An event related to the AI-Robotics coordination effort.
As the the field of robotics matures, the construction of ever more intelligent robots becomes possible. For many of the challenging tasks we want robots to perform it is crucial that the robot can be provided with knowledge: knowledge of its capabilities, of its environment, and of how the former interacts with the latter. The fields of AI and robotics have many approaches to representation and reasoning. This symposium focusses on one approach which has been growing in popularity across these communities in recent years: qualitative representations. Such representations abstract away from the quantitative representations that underlie many physically situated systems, providing more compact, structured representations which omit (unnecessary) detail. Qualitative representations exist for many aspects of space and time; action; uncertainty; and categorical knowledge (ontologies).
Qualitative representations have many advantages, including naturally encoding semantics for many systems, being accessible to humans, providing smaller state spaces for learning and reasoning, and also suitable for communication via natural language. These advantages have seen them being increasingly used in intelligent physically-grounded systems, from encoding spatial configurations of objects, to modelling human behaviour over time. This work is being done in many different places, and across different subfields of AI such as knowledge representation and reasoning, planning, uncertainty, learning, and perception. We strongly believe that the time is now right to bring these disparate groups together to share experiences and technical knowledge. We also wish to connect the new applied work being done with qualitative representations in robotics to the rich history of related ideas in AI.
The symposium will include invited talks, presentations on accepted papers, discussion and demonstrations. This event runs in parallel with the symposium on Knowledge Representation and Reasoning in Robotics. Due to the overlapping nature of these events, we will have joint sessions and coordinate our activities.
| Time | Talk |
|---|---|
| 08:45 - 09:00 | Welcome remarks |
| 09:00 - 10:00 | Invited Talk: Jeffrey Siskind, Purdue University Seeing, Saying, Doing, and Thinking: The compositional structure of perception, language, action, and thought |
| 10:00 - 10:30 | Grounding Language in Perception for Scene Conceptualization in Autonomous Robots Krishna Dubba, Miguel de Oliveira, Gi Lim, Luis Lopes, Anthony Cohn, David Hogg |
| 10:30 - 11:00 | Coffee Break |
| 11:00 - 11:30 | A Probabilistic Model of Human-Robot Spatial Interaction using a Qualitative Trajectory Calculus Christian Dondrup, Marc Hanheide and Nicola Bellotto |
| 11:30 - 12:00 | Multi-robot Human Guidance using Topological Graphs Piyush Khandelwal and Peter Stone |
| 12:00 - 12:30 | From Sequence to Trajectory and Vice-Versa: Solving the Inverse QTC Problem and Coping with Real-World Trajectories Konstantinos Iliopoulos, Nikolaos Mavridis, and Nicola Bellotto (presented by Christian Dondrup) |
| 12:30 - 14:00 | Lunch Break |
| 14:00 - 15:00 | Invited Talk: Daniele Nardi, Sapienza University of Rome Representing Knowledge About Environments: Semantic Mapping |
| 15:00 - 15:30 | Ontology-based Cognitive System for Contextual Reasoning in Robot Architectures Alessandro Oltramari, Yury Vinokurov, Christian Lebiere, Jean Oh, and Anthony Stentz |
| 15:30 - 16:00 | Coffee Break |
| 16:00 - 16:30 | Effects of Training Data Variation and Temporal Representation in a QSR-Based Action Prediction System Jay Young and Nick Hawes |
| 16:30 - 17:00 | A qualitative representation of social conventions for application in robotics Frank Dylla, Arne Kreutzmann and Diedrich Wolter |
| 17:00 - 17:30 | Posters + Discussion |
| 09:00 - 10:00 | Invited Talk: Anthony Cohn, University of Leeds Learning Qualitative Spatio-Temporal Activity Models |
| 10:00 - 10:30 | Probabilistic Logic for Multi-Robot Event Recognition J Angelo Gurzoni Jr, Paulo Santos |
| 10:30 - 11:00 | Coffee Break |
| 11:00 - 11:30 | A Planner for Ambient Assisted Living: From high-level reasoning to low-level robot execution and back Maurizio Di Rocco, Subhash Sathyakeerthy, Jasmin Grosinger, Federico Pecora, Alessandro Saffiotti, Filippo Cavallo, Bonaccorsi Manuele, Raffaele Limosani, Alessandro Manzi, Giancarlo Teti and Paolo Dario. |
| 11:30 - 12:00 | Planning Domain + Execution Semantics: a Way Towards Robust Execution? Stefan Konecny, Sebastian Stock, Federico Pecora and Alessandro Saffiotti |
| 12:00 - 12:30 | Invited Talk: Matthew Klenk, PARC. The Role of Context in Spatial Region Identification |
| 12:30 - 14:00 | Lunch Break |
| 14:00 - 15:00 | Invited Talk: Michael Gelfond, Texas Tech University Logic Programing and Probabilistic Reasoning: The P-log Perspective |
| 15:00 - 15:30 | Knowledge-Based Reasoning on Semantic Maps Roberto Capobianco, Guglielmo Gemignani, Daniele Nardi, Domenico Bloisi, and Luca Iocchi |
| 15:30 - 16:00 | Coffee Break |
| 16:00 - 16:30 | Towards a Similarity between Qualitative Image Descriptions for Comparing Real Scenes Zoe Falomir Llansola, Lledó Museros and Luis Gonzalez-Abril |
| 16:30 - 17:00 | Scene Interpretation for Self-Aware Cognitive Robots Melodi Ozturk, Mustafa Ersen, Melis Kapotoglu, Cagatay Koc, Sanem Sariel-Talay and Hulya Yalcin |
| 17:00 - 17:30 | Posters + Discussion |
| 09:00 - 10:00 | Invited Talk: Mary-Anne Williams, University of Technology, Sydney Social Robots and the Role of Attention |
| 10:00 - 10:30 | Planning in Answer Set Programming while Learning Action Costs for Mobile Robots Fangkai Yang, Piyush Khandelwal, Matteo Leonetti, and Peter Stone |
| 10:30 - 11:00 | Coffee Break |
| 11:00 - 11:30 | Bootstrapping Probabilistic Models of Qualitative Spatial Relations for Active Visual Object Search Lars Kunze, Chris Burbridge, Nick Hawes |
| 11:30 - 12:00 | An Approach for Scene Interpretation using Qualitative Descriptors, Semantics and Domain Knowledge Zoe Falomir |
| 12:00 - 12:30 | Relational approaches for joint object classification and scene similarity measurement in indoor environments Marina Alberti, John Folkesson, Patric Jensfelt |
Nick Hawes (n.a.hawes@cs.bham.ac.uk)
School of Computer Science, University of Birmingham, UK
Chris Burbridge and Lars Kunze
School of Computer Science,
University of Birmingham,
Edgbaston, Birmingham, B15 2TT, UK
c.j.c.burbridge@cs.bham.ac.uk and l.kunze@cs.bham.ac.uk
Alper Aydemir
Computer Vision Group
NASA Jet Propulsion Laboratory,
4800 Oak Grove Drive, Pasadena, California 91109, USA
alper.o.aydemir@jpl.nasa.gov
Marc Hanheide and Nicola Bellotto
School of Computer Science,
University of Lincoln,
Brayford Pool, Lincoln, LN6 7TS,
mhanheide@lincoln.ac.uk and nbellotto@lincoln.ac.uk
Luca Iocchi and Daniele Nardi
Dipartimento di Ingegneria Informatica,
Automatica e Gestionale "A. Ruberti",
"Sapienza" Universita' di Roma,
Via Ariosto 25, 00185 ROMA, Italy iocchi@dis.uniroma1.it and nardi@dis.uniroma1.it
Patric Jensfelt and John Folkesson
Centre for Autonomous Systems,
Kungliga Tekniska Högskolan, Teknikringen 14, plan7, SE-114 28 Stockholm, Sweden
patric@csc.kth.se and johnf@csc.kth.se
Michael Karg
Technische Universität München,
Department of Computer Science,
Informatik 9, Boltzmannstrasse 3, 85748 Garching, Germany
kargm@in.tum.de
John D. Kelleher
School of Computing, Dublin Institute of Technology,
Kevin Street, Dublin 8, Ireland
john.d.kelleher@dit.ie
Alexandra Kirsch
University of Tübingen,
Department of Computer Science,
Sand 14, 72076 Tübingen, Germany
alexandra.kirsch@uni-tuebingen.de
Matthew Klenk
Palo Alto Research Center,
3333 Coyote Hill Rd Palo Alto, CA 94304, USA
matthew.klenk@parc.com
Kate Lockwood
Computer Science and Information Technology,
California State University, Monterey Bay,
100 Campus Center, Seaside, CA 93955-8001, USA
klockwood@csumb.edu
Fiona McNeill
University of Edinburgh,
School of Informatics,
10 Crichton Street, Edinburgh, EH8 9LE, UK
f.j.mcneill@ed.ac.uk
Andrzej Pronobis
Robotics and State Estimation Lab,
University of Washington, Seattle, WA 98195-2350, USA
pronobis@cs.washington.edu
Diedrich Wolter
FB3 - Informatics,
Universität Bremen,
P.O. Box 330 440, 28334 Bremen, Germany
dwolter@informatik.uni-bremen.de
Jure Zabkar
AI Lab, Faculty of Comp. & Inf. Science,
University of Ljubljana,
Trzaska 25, SI-1000 Ljubljana, Slovenia
jure.zabkar@fri.uni-lj.si