Grasp Learning by Means of Developing Sensorimotor Schemas and Generic World Knowledge

We present a cognitive system in which grasping competences are coded by means of a formalisation of sensory motor schemas in terms of so called ‘object action complexes’ (OACs). OACs define the knowledge of the system via the effects and precondition of certain behavioural patterns, and also code the uncertainty associated with their execution. OACs are grounded through the observation and evaluation of individual executions generating ‘experiments’, and dynamically adapt through using these experiments for learning. Moreover, in parallel with the development and refinement of OACs, generic world knowledge is permanently generated by the system which affects the OACs on a meta level and provides a means for the generation of new competences and better generalisation. We present an example of a developing system executing OACs which code the grasping of known and unknown objects, and thereby illustrate (i) the refinement of OACs and (ii) building up generic world knowledge. We see this as particularly important since these interaction processes, although fundamental for human development, are usually difficult to observe by means of techniques in neurophysiology and developmental psychology.

[1]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[2]  Henrik I. Christensen,et al.  Automatic grasp planning using shape primitives , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[3]  Zoe Kourtzi,et al.  Development of visually evoked cortical activity in infant macaque monkeys studied longitudinally with fMRI. , 2006, Magnetic resonance imaging.

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

[5]  Danica Kragic,et al.  Learning grasping points with shape context , 2010, Robotics Auton. Syst..

[6]  Filipo Studzinski Perotto,et al.  Constructivist Anticipatory Learning Mechanism ( CALM ) – dealing with partially deterministic and partially observable environments , 2007 .

[7]  J. Piaget.  The construction of reality in the child , 1954 .

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

[9]  Justus H. Piater,et al.  Refining grasp affordance models by experience , 2010, 2010 IEEE International Conference on Robotics and Automation.

[10]  Benjamin Kuipers,et al.  Autonomous Development of a Grounded Object Ontology by a Learning Robot , 2007, AAAI.

[11]  P. L. Adams.  THE ORIGINS OF INTELLIGENCE IN CHILDREN , 1976 .

[12]  J. Piaget.  The Psychology Of Intelligence , 1951 .

[13]  Florentin Wörgötter,et al.  International Journal of Humanoid Robotics c ○ World Scientific Publishing Company Visual Primitives: Local, Condensed, Semantically Rich Visual Descriptors and their Applications in Robotics , 2022 .

[14]  Christopher W. Geib,et al.  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 , 2022 .

[15]  R. Brooks,et al.  Petitagé: A Case Study in Developmental Robotics , 2001 .

[16]  Stephen Hart,et al.  Learning Generalizable Control Programs , 2011, IEEE Transactions on Autonomous Mental Development.

[17]  Sinan Kalkan,et al.  Using multi-modal 3D contours and their relations for vision and robotics , 2010, J. Vis. Commun. Image Represent..

[18]  K. Fischer.  A theory of cognitive development: The control and construction of hierarchies of skills. , 1980 .

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

[20]  Karen E Adolph,et al.  Learning to keep balance. , 2002, Advances in child development and behavior.

[21]  Vijay Kumar,et al.  Robotic grasping and contact: a review , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[22]  J. Lockman.  A perception--action perspective on tool use development. , 2000, Child development.

[23]  Norbert Krüger,et al.  Temporal accumulation of oriented visual features , 2011, J. Vis. Commun. Image Represent..

[24]  Risto Miikkulainen,et al.  The constructivist learning architecture: a model of cognitive development for robust autonomous robots , 2004 .

[25]  Michael A. Arbib,et al.  Schema-based learning: towards a theory of organization for biologically-inspired autonomous agents , 1997, AGENTS '97.

[26]  R. Schranner.  Dynamic systems , 1977, Nature.

[27]  Ad W. Smitsman,et al.  Perseveration in Tool Use: A Window for Understanding the Dynamics of the Action-Selection Process , 2008 .

[28]  Linda B. Smith,et al.  Development through Sensorimotor Coordination , 2010 .

[29]  A. Baddeley.  Essentials of Human Memory , 1999 .

[30]  Lawson L. S. Wong,et al.  Learning Grasp Strategies with Partial Shape Information , 2008, AAAI.

[31]  Justus H. Piater,et al.  Development of Object and Grasping Knowledge by Robot Exploration , 2010, IEEE Transactions on Autonomous Mental Development.

[32]  Justus H. Piater,et al.  Developing haptic and visual perceptual categories for reaching and grasping with a humanoid robot , 2001, Robotics Auton. Syst..

[33]  A. Karmiloff-Smith,et al.  The cognizer's innards: A psychological and philosophical perspective on the development of thought. , 1993 .

[34]  Emre Ugur,et al.  Affordance learning from range data for multi-step planning , 2009, EpiRob.

[35]  Danica Kragic,et al.  Minimum volume bounding box decomposition for shape approximation in robot grasping , 2008, 2008 IEEE International Conference on Robotics and Automation.