Towards Affordance-Based Robot Control: International Seminar, Dagstuhl Castle, Germany, June 5-9, 2006, Revised Papers (Lecture Notes in Computer Science, 4760)

Today’s mobile robot perception is insufficient for acting goal-directedly in unconstrained, dynamic everyday environments like a home, a factory, or a city. Subject to restrictions in bandwidth, computer power, and computation time, a robot has to react to a wealth of dynamically changing stimuli in such environments, requiring rapid, selective attention to decisive, action-relevant information of high current utility. Robust and general engineering methods for effectively and efficiently coupling perception, action and reasoning are unavailable. Interesting performance, if any, is currently only achieved by sophisticated robot programming exploiting domain features and specialties, which leaves ordinary users no chance of changing how the robot acts. The purpose of this volume - outcome of a GI-Dagstuhl Seminar held in Dagstuhl Castle in June 2006 - is to give a first overview on the concept of affordances for the design and implementation of autonomous mobile robots acting goal-directedly in a dynamic environment. The aim is to develop affordance-based control as a method for robotics. The potential of this new methodology will be shown by going beyond navigation-like tasks towards goaldirected autonomous manipulation in the project demonstrators. Interpersonal Maps: How To Map Affordances For Interaction Behaviour / Verena V. Hafner And Frederic Kaplan -- Does It Help A Robot Navigate To Call Navigability An Affordance? / Joachim Hertzberg, Kai Lingemann, Christopher Lorken, Andreas Nuchter And Stefan Stiene -- Learning Causality And Intentional Actions / Somboon Hongeng And Jeremy Wyatt -- Gram: Reasoning With Grounded Action Models By Combining Knowledge Representation And Data Mining / Nicolai V. Hoyningen-huene, Bernhard Kirchlechner And Michael Beetz -- Affordance-based Human-robot Interaction / Reinhard Moratz And Thora Tenbrink -- Reinforcement Learning Of Predictive Features In Affordance Perception / Lucas Paletta And Gerald Fritz -- Functional Model For Affordance-based Agents / Martin Raubal And Reinhard Moratz -- Affordances In An Ecology Of Physically Embedded Intelligent Systems / Alessandro Saffiotti And Mathias Broxvall -- Use Of Affordances In Geospatial Ontologies / Sumit Sen -- Learning The Affordances Of Tools Using A Behavior-grounded Approach / Alexander Stoytchev -- Function-based Reasoning For Goal-oriented Image Segmentation / Melanie A. Sutton And Louise Stark -- Macs Project: An Approach To Affordance-inspired Robot Control / Erich Rome, Lucas Paletta, Erol Sahin, Georg Dorffner, Joachim Hertzberg, Ralph Breithaupt, Gerald Fritz, Jorg Irran, Florian Kintzler, Christopher Lorken, Stefan May And Emre Ugur. Erich Rome, Joachim Hertzberg, Georg Dorffner (eds.). Includes Bibliographical References And Index. Today’s Mobile Robot Perception Is Insu?cient For Acting Goal-directedly In - Constrained, Dynamic Everyday Environments Like A Home, A Factory, Or A City. Subject To Restrictions In Bandwidth, Computer Power, And Computation Time, A Robot Has To React To A Wealth Of Dynamically Changing Stimuli In Such - Vironments, Requiring Rapid, Selective Attention To Decisive, Action-relevant - Formation Of High Current Utility. Robust And General Engineering Methods For E?ectively And E?ciently Coupling Perception, Action, And Reasoning Are Unava- Able. Interesting Performance, If Any, Is Currently Only Achieved By Sophisticated Robot Programming Exploiting Domain Features And Specialties, Which Leaves - Dinary Users No Chance Of Changing How The Robot Acts. The Latter Facts Are High Barriers For Introducing, For Example, Service Robots Into Human Living Or Work Environments. In Order To Overcome These Barriers, Additonal R&d E?orts Are Required. The European Commission Is Undert- Ing A Determined E?ort To Fund Related Basic, Inter-disciplinary Research In A Line Of Strategic Objectives, Including The Cognitive Systems Calls In Their 6th Framework Programme (fp6, [1]), And Continuing In The 7th Framework P- Gramme.oneofthefundedcognitivesystemsprojectsismacs(“multi-sensory Autonomous Cognitive Systems Interacting With Dynamic Environments For P- Ceiving And Using A?ordances”). Front Matter....Pages - Interpersonal Maps: How to Map Affordances for Interaction Behaviour....Pages 1-15 Does It Help a Robot Navigate to Call Navigability an Affordance?....Pages 16-26 Learning Causality and Intentional Actions....Pages 27-46 GrAM: Reasoning with Grounded Action Models by Combining Knowledge Representation and Data Mining....Pages 47-62 Affordance-Based Human-Robot Interaction....Pages 63-76 Reinforcement Learning of Predictive Features in Affordance Perception....Pages 77-90 A Functional Model for Affordance-Based Agents....Pages 91-105 Affordances in an Ecology of Physically Embedded Intelligent Systems....Pages 106-121 Use of Affordances in Geospatial Ontologies....Pages 122-139 Learning the Affordances of Tools Using a Behavior-Grounded Approach....Pages 140-158 Function-Based Reasoning for Goal-Oriented Image Segmentation....Pages 159-172 The MACS Project: An Approach to Affordance-Inspired Robot Control....Pages 173-210 Back Matter....Pages -