Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program GRASP Emergence of Cognitive Grasping through.

Slides:



Advertisements
Similar presentations
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
Advertisements

DoD FEAC Activity and Data Modeling in Perspective Dennis E. Wisnosky Wizdom Systems, Inc
University of Minho School of Engineering Centre ALGORITMI Uma Escola a Reinventar o Futuro – Semana da Escola de Engenharia - 24 a 27 de Outubro de 2011.
Jenkins — Modular Perception and Control Brown Computer — ROUGH DRAFT ( ) 1 Workshop Introduction: Modular Perception.
Yiannis Demiris and Anthony Dearden By James Gilbert.
Systems Engineering in a System of Systems Context
KAIST CS780 Topics in Interactive Computer Graphics : Crowd Simulation A Task Definition Language for Virtual Agents WSCG’03 Spyros Vosinakis, Themis Panayiotopoulos.
Knowledge Acquisitioning. Definition The transfer and transformation of potential problem solving expertise from some knowledge source to a program.
CPSC 695 Future of GIS Marina L. Gavrilova. The future of GIS.
Provisional draft 1 ICT Work Programme Challenge 2 Cognition, Interaction, Robotics NCP meeting 19 October 2006, Brussels Colette Maloney, PhD.
4. Interaction Design Overview 4.1. Ergonomics 4.2. Designing complex interactive systems Situated design Collaborative design: a multidisciplinary.
Presented by Gal Peleg CSCI2950-Z, Brown University February 8, 2010 BY CHARLES C. KEMP, AARON EDSINGER, AND EDUARDO TORRES-JARA (March 2007) 1 IEEE Robotics.
Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Cognitive Robots © 2014, SNU CSE Biointelligence Lab.,
Institute of Perception, Action and Behaviour (IPAB) Director: Prof. Sethu Vijayakumar.
Darema Dr. Frederica Darema NSF Dynamic Data Driven Application Systems (Symbiotic Measurement&Simulation Systems) “A new paradigm for application simulations.
1 Challenge 2 Call 3 presentation to NCPs Brussels, December 13, 2007 Colette Maloney, PhD Head of Unit, INFSO E5, Cognitive Systems and Robotics European.
Zhiyong Wang In cooperation with Sisi Zlatanova
Break-out Group # D Research Issues in Multimodal Interaction.
Visualizing Information in Global Networks in Real Time Design, Implementation, Usability Study.
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
Prediction in Human Presented by: Rezvan Kianifar January 2009.
Vision-Based Reach-To-Grasp Movements From the Human Example to an Autonomous Robotic System Alexa Hauck.
Cognitive Architectures: A Way Forward for the Psychology of Programming Michael Hansen Ph.D Student in Comp/Cog Sci CREST / Percepts & Concepts Lab Indiana.
Beyond Gazing, Pointing, and Reaching A Survey of Developmental Robotics Authors: Max Lungarella, Giorgio Metta.
The aim of GRASP is the design of a cognitive system capable of performing grasping and manipulation tasks in open-ended environments, dealing with novelty,
Synthetic Cognitive Agent Situational Awareness Components Sanford T. Freedman and Julie A. Adams Department of Electrical Engineering and Computer Science.
The roots of innovation Future and Emerging Technologies (FET) Future and Emerging Technologies (FET) The roots of innovation Proactive initiative on:
Chapter 2.2 Game Design. CS Overview This introduction covers: –Terms –Concepts –Approach All from a workaday viewpoint.
1 Introduction to Software Engineering Lecture 1.
MURI: Integrated Fusion, Performance Prediction, and Sensor Management for Automatic Target Exploitation 1 Dynamic Sensor Resource Management for ATE MURI.
EU Project MACS Multi-sensory Autonomous Cognitive Systems Interacting with Dynamic Environments for Perceiving and Using Affordances Erich Rome Robot.
Project ArteSImit Artefact Structural Learning through Imitation (TU München, U Parma, U Tübingen, U Minho, KU Nijmegen) Giorgio Panin - TUM.
A Context Model based on Ontological Languages: a Proposal for Information Visualization School of Informatics Castilla-La Mancha University Ramón Hervás.
Systems Biology ___ Toward System-level Understanding of Biological Systems Hou-Haifeng.
DARPA ITO/MARS Project Update Vanderbilt University A Software Architecture and Tools for Autonomous Robots that Learn on Mission K. Kawamura, M. Wilkes,
Natural Tasking of Robots Based on Human Interaction Cues Brian Scassellati, Bryan Adams, Aaron Edsinger, Matthew Marjanovic MIT Artificial Intelligence.
Deformable object registration/fitting (Chavo, TUM) Grasp selection (Beatriz, UJI) Differently scaled object model DB (Walter, TUW) Classification and.
Abstract This presentation questions the need for reinforcement learning and related paradigms from machine-learning, when trying to optimise the behavior.
Introduction to Artificial Intelligence CS 438 Spring 2008 Today –AIMA, Ch. 25 –Robotics Thursday –Robotics continued Home Work due next Tuesday –Ch. 13:
MODEL-BASED SOFTWARE ARCHITECTURES.  Models of software are used in an increasing number of projects to handle the complexity of application domains.
Chapter 1. Cognitive Systems Introduction in Cognitive Systems, Christensen et al. Course: Robots Learning from Humans Park, Sae-Rom Lee, Woo-Jin Statistical.
1 Chapter 8 Building the Analysis Model (1) Analysis Concepts and Principles.
Chapter 10. The Explorer System in Cognitive Systems, Christensen et al. Course: Robots Learning from Humans On, Kyoung-Woon Biointelligence Laboratory.
Internet of Things. IoT Novel paradigm – Rapidly gaining ground in the wireless scenario Basic idea – Pervasive presence around us a variety of things.
MindRACES, First Review Meeting, Lund, 11/01/ Anticipatory Behavior for Object Recognition and Robot Arm Control Modular and Hierarchical Systems,
RULES Patty Nordstrom Hien Nguyen. "Cognitive Skills are Realized by Production Rules"
NCP Info DAY, Brussels, 23 June 2010 NCP Information Day: ICT WP Call 7 - Objective 1.3 Internet-connected Objects Alain Jaume, Deputy Head of Unit.
Real Time Collaboration and Sharing
6 th Framework Programme - Priority 2 “Information Society Technologies” FP6/2003/IST/2 Joint Action Science and Technology JAST - FP Joint-Action.
Chapter 4 Motor Control Theories Concept: Theories about how we control coordinated movement differ in terms of the roles of central and environmental.
Slide no 1 Cognitive Systems in FP6 scope and focus Colette Maloney DG Information Society.
WP6 Emotion in Interaction Embodied Conversational Agents WP6 core task: describe an interactive ECA system with capabilities beyond those of present day.
Atos, Atos and fish symbol, Atos Origin and fish symbol, Atos Consulting, and the fish symbol itself are registered trademarks of Atos Origin SA. June.
Systems Architectures System Integration & Architecture.
A Generic Model for Software Architecture Yun Sang-hyun Rossak. W. / Kirova. V. / Jolian. L. / Lawson. H. / Zemel. T. Software, IEEE Jul/Aug.
Ali Ghadirzadeh, Atsuto Maki, Mårten Björkman Sept 28- Oct Hamburg Germany Presented by Jen-Fang Chang 1.
Technische Universität München © Prof. Dr. H. Krcmar An Ontology-based Platform to Collaboratively Manage Supply Chains Tobias Engel, Manoj Bhat, Vasudhara.
Functionality of objects through observation and Interaction Ruzena Bajcsy based on Luca Bogoni’s Ph.D thesis April 2016.
WP 7: Management Stipulated versus actual work
PostGraduate Research Excellence Symposium (PGReS) 2015
San Diego May 22, 2013 Giovanni Saponaro Giampiero Salvi
IPAB Research Areas and Strengths
GRASP Management Meeting March Munich
Scenario and Integration in GRASP
Seven Principles of Synthetic Intelligence
Today: Classic & AI Control Wednesday: Image Processing/Vision
On Using Semantic Complex Event Processing for Dynamic Demand Response
Hardware and system development:
Smart Learning concepts to enhance SMART Universities in Africa
John D. McGregor Module 6 Session 1 More Design
Presentation transcript:

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program GRASP Emergence of Cognitive Grasping through Emulation, Introspection and Surprise Danica Kragic

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program GRASP  Challenge 2: Cognitive Systems, Interaction, Robotics  March 2008 – February 2012  Project officer: Mr Mariusz Baldyga  Coordinator: Danica Kragic (KTH)  Co-coordinator: Markus Vincze (TUW)  Administrator: Jeanna Ayoubi (KTH)  Project number:

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Consortium University of Karlsruhe Karlsruhe, Germany T. Asfour, R. Dillmann Kungliga Tekniska Högskolan Stockholm, Sweden D. Kragic, P. Jensfelt Lappeenranta University of Technology, Lappeenranta, Finland V. Kyrki & H. Handroos Technische Universität München, Munich Germany D. Burschka, H. Deubel Technische Universität Wien, Vienna, Austria M. Vincze Universitat Jaume I, Castellón, Spain A. Morales, P. Sanz Otto Bock, Austria OB H. Dietl GRASP Foundation for Research and Technology - Hellas, Greece A. Argyros & M. Lourakis

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Introduction  GRASP is a project with a focused target  Objectives Theory of grasp modeling Self and context-awareness Curiosity and surprise driven behavior New grasping strategies Exploitation and evaluation for future prosthesis, industrial and service markets  Grasping and manipulation as a control problem have been studied since the beginning of robotics: HOWEVER- very little has been done in terms of cognitive aspects of grasping, implementation and evaluation of systems - this is what GRASP is about  Still a huge gap between visual servoing and grasping

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program GRASP: Concept and Objectives  “Robots handling individually or jointly....” GRASP proposes a generic predict-act-perceive paradigm for grasping and manipulation of objects, dealing with static and dynamic properties of objects, the environment and the task.  Cognitive approach: predict – act – perceive Generic principle of human brain  Paradigm open to development Unsupervised, fully autonomously, new objects  Clear application domain: grasping  Measurable benchmark: empty basket, fill pallet  Expected results: Grasping ontology Proof or disproof of paradigm

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Worpackages 1. Learning to Observe Human Grasping and Consequences of Grasping 2. Representations and Ontology for Learning and Abstraction of Grasping 3. Self-experience of Grasping and Multimodal Grounding 4. Perceiving Grasping Context and Interlinking Contextual Knowledge 5. Surprise: Detecting the Unexpected and Learning from it 6. Introspection and Prediction through Simulation 7. Cognitive Robotic Grasping - Integration and Applications

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Relationship between WPs

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Major Milestones

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Platforms, sensory feedback No new hardware development in GRASP

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program From simulation to real world and back WP1 What/Where/How WP7 Integration and Applications

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Research objectives  Goal: filter action relevant from action-irrelevant stimuli to enhance the manipulation performance; analyse, for a variety of increasingly complex sensorimotor tasks, the spatial and temporal properties of selective visual processing before and during manual reaching and grasping movements of human actors.  WP1: Kinematics and grasping forces, together with the eye gaze behaviour during the grasp will be measured/tracked.  WP2, WP7 – the definition of the ontologies requires definitions of action specific, selective visuo-spatial processes  WP3, WP4, WP6 – representations of control parameters, object and body (hardware) attributes  WP5 - eye-gaze positions: What to look for? What to disregard?

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Major Milestones – month 12 1 Spatio-temporal representation of human body and hands, mapping to different robot embodiments; initial evaluation on a humanoid platform. WP1, WP2, WP7 FORTH 2 Definition of initial ontology based on human studies; acquisition (perception and formalisation) of knowledge through hand-environment interaction. WP1, WP2, WP4, WP5 KTH 3 Initial design of the control and engine architectures; evaluation of the perception-action planning cycle in simulation. WP3, WP4, WP6, WP7 LUT

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Major Milestones – month 24 4 Analysis of action-specific visuo-spatial processing, vocabulary of human actions/interactions for perception of task relations and affordances. WP1, WP2, WP4, WP5 TUW 5 Implementation of high-level controllers including a global uncertainty model, integration and evaluation in the simulator and experimental platforms, grounding grasping primitives. WP3, WP6, WP7UniKarl 6 Integration and evaluation of human body and hand tracking on active robot heads, demonstration of a grasping cycle on the experimental platforms. WP1, WP2, WP4, WP7 TUM

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Major Milestones – month 36 7 Observing consequences of grasping; vocabulary of robot action/interactions and definition of a hierarchical structure of features. WP1, WP2, WP4, WP5 FORTH 8 Implementation of hybrid controllers for on-line adaptive primitive grounding; evaluation in the simulator and on experimental platforms. WP3, WP6, WP7 LUT 9 Integrating contextual representation in the ontology and development of the attention system with view planning; implementation on active head. WP1, WP2, WP5, WP7 TUM

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Major Milestones – month Linking structure, affordances, actions and tasks; evaluation of representations defined by the ontology. WP2, WP4TUW 11 Integration and evaluation of scenarios on multiple experimental platforms, demonstration of cognitive capabilities of robots. AllUniKarl

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program Everything will be open source The simulator Hand models Tracking algorithms Vision algorithms Object and action representations Database with human data Software framework for testing and benchmarking

Emergence of Cognitive Grasping through Emulation, Introspection and Surprise GRASP EUl 7 th Framework Program THE END