Title of the Deliverable: Publication about Multi-level Learning Sys- Tem Attachment 1 Attachment 2 a Formal Definition of Object-action Complexes and Examples at Different Levels of the Processing Hierarchy

In this report the authors define and describe the concept of Object-Action Complexes and give some examples. OACs combine the concept of affordance with the computational efficiency of STRIPS. Affordance is the relation between a situation and the action that it allows. OACs are proposed as a framework for representing actions, objects and the learning process that constructs such representations at all levels. Formally, an OAC is defined as a triplet, composed of a unique ID, a predition function that codes the systems belief on how the world (which is defined as a kind of global attribute space) will change after applying the OAC and a statisical measure representing the success of an OAC. The prediction function is thereby a mapping within the global attribute space. The measurement captures the accuracy of this prediction function and describes the reliability of the OAC. Therefore, it can be used for optimal decision making, predicion of the outcome of a certain action and learning.

[1]  Marek J. Sergot,et al.  A logic-based calculus of events , 1989, New Generation Computing.

[2]  Maya Cakmak,et al.  To Afford or Not to Afford: A New Formalization of Affordances Toward Affordance-Based Robot Control , 2007, Adapt. Behav..

[3]  Carme Torras,et al.  Learning Inverse Kinematics: Reduced Sampling Through Decomposition Into Virtual Robots , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Christopher W. Geib,et al.  Representation and Integration: Combining Robot Control, High-Level Planning, and Action Learning , 2008 .

[5]  Mark Steedman,et al.  Plans, Affordances, And Combinatory Grammar , 2002 .

[6]  Markus Lappe,et al.  Biologically Motivated Multi-modal Processing of Visual Primitives , 2003 .

[7]  Babette Dellen,et al.  Ascertaining relevant changes in visual data by interfacing AI reasoning and low-level visual information via temporally stable image segments data , 2008 .

[8]  Danica Kragic,et al.  A strategy for grasping unknown objects based on co-planarity and colour information , 2010, Robotics Auton. Syst..

[9]  Nicolas Pugeault,et al.  Early cognitive vision: feedback mechanisms for the disambiguation of early visual representation , 2008 .

[10]  Danica Kragic,et al.  Selection of robot pre-grasps using box-based shape approximation , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Minija Tamosiunaite,et al.  Learning to reach by reinforcement learning using a receptive field based function approximation approach with continuous actions , 2009, Biological Cybernetics.

[12]  Tamim Asfour,et al.  Object separation using active methods and multi-view representations , 2008, 2008 IEEE International Conference on Robotics and Automation.

[13]  R. Hetherington.  The Perception of the Visual World , 1952 .

[14]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[15]  Richard Fikes,et al.  STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving , 1971, IJCAI.

[16]  Florentin Wörgötter,et al.  Cognitive agents - a procedural perspective relying on the predictability of Object-Action-Complexes (OACs) , 2009, Robotics Auton. Syst..

[17]  Andrej Gams,et al.  Generalization of example movements with dynamic systems , 2009, 2009 9th IEEE-RAS International Conference on Humanoid Robots.

[18]  Tamim Asfour,et al.  Imitation Learning of Dual-Arm Manipulation Tasks in Humanoid Robots , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[19]  Danica Kragic,et al.  Simultaneous Visual Recognition of Manipulation Actions and Manipulated Objects , 2008, ECCV.

[20]  Christopher W. Geib,et al.  Object Action Complexes as an Interface for Planning and Robot Control , 2006 .

[21]  Gordon Cheng,et al.  Synthesizing goal-directed actions from a library of example movements , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.

[22]  Fabien Scalzo,et al.  Vision as Inference in a Hierarchical Markov Network , 2008 .

[23]  Mark Steedman,et al.  Computational Grammar Acquisition from CHILDES Data Using a Probabilistic Parsing Model , 2009 .

[24]  Justus H. Piater,et al.  A Probabilistic Framework for 3D Visual Object Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Danica Kragic,et al.  Birth of the Object: Detection of Objectness and Extraction of Object Shape through Object-Action complexes , 2008, Int. J. Humanoid Robotics.

[26]  Charles D. Yang,et al.  Knowledge and learning in natural language , 2000 .

[27]  Danica Kragic,et al.  Primitive-Based Action Representation and Recognition , 2011, Adv. Robotics.

[28]  Ales Ude,et al.  Sensorimotor processes for learning object representations , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.

[29]  Carme Torras,et al.  Action rule induction from cause-effect pairs learned through robot-teacher interaction , 2008 .

[30]  Mark Steedman,et al.  Using Kernel Perceptrons to Learn Action Effects for Planning , 2008 .

[31]  Gordon Cheng,et al.  Making Object Learning and Recognition an Active Process , 2008, Int. J. Humanoid Robotics.

[32]  N. Krüger,et al.  Autonomous Learning of Object-specific Grasp Affordance Densities , 2009 .

[33]  B. Porr,et al.  Path-finding in real and simulated rats: On the usefulness of forgetting and frustration for navigation learning , 2007 .

[34]  Ales Ude,et al.  Learning primitive actions through object exploration , 2008, Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots.

[35]  Carme Torras,et al.  On-line learning of macro planning operators using probabilistic estimations of cause-effects , 2008 .

[36]  Danica Kragic,et al.  Early reactive grasping with second order 3D feature relations , 2007 .

[37]  Carme Torras,et al.  Learning rules from cause-effects explanations , 2008 .

[38]  Fahiem Bacchus,et al.  A Knowledge-Based Approach to Planning with Incomplete Information and Sensing , 2002, AIPS.

[39]  Stefan Schaal,et al.  2008 Special Issue: Reinforcement learning of motor skills with policy gradients , 2008 .

[40]  Luke S. Zettlemoyer,et al.  Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars , 2005, UAI.

[41]  Gordon Cheng,et al.  Coaching: An Approach to Efficiently and Intuitively Create Humanoid Robot Behaviors , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[42]  Raymond J. Mooney,et al.  Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus , 2007, ACL.

[43]  Mark Steedman,et al.  Exploration and Planning in a Three-Level Cognitive Architecture , 2008 .

[44]  Danica Kragic,et al.  Visual recognition of grasps for human-to-robot mapping , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[45]  Ales Ude,et al.  Motion imitation and recognition using parametric hidden Markov models , 2008, Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots.