Towards a Smart World—
Evolving Technologies in AI

Artificial Intelligence has always been the frontier discipline of Computer Science. AI technologies have gradually permeated our living environments.

Intelligent products have become an ubiquituous mainstay, while the goals of AI continuously move on to meet new, exciting challenges. 2011's annual German AI conference, KI 2011, has had a focus on technologies for a smarter world, and attracted contributions from many areas of AI research.

The conference proceedings are available from Springer (LNAI 7006).


Co-Located with

INFORMATIK 2011   MATES 2011

Informatik 2011—41. Jahrestagung der Gesellschaft für Informatik
MATES 2011—9th German Conference on Multi-Agent System Technologies

Full program

Your KI 2011 ticket includes attendance for the co-located events (Informatik 2011 and MATES 2011).

Check out our interactive conference planner: It gives you a full list of events (without any guarantees for correctness), and comes with calendar export.
(We would be thankful for feedback on any problems and issues with that tool.)

Tuesday, Oct 4, 2011
08:00 - 18:00 Registration
09:00 - 10:30 see WS pageWorkshops MA544Tutorials H0236General Game Playing
10:30 - 11:00 Coffee Break
11:00 - 12:30 Workshops H2037C. Schäfer (DAAD): Fördermöglichkeiten für Ausland u. Kooperation
A. Rabe (DIA): Karriere in IT und Informatik
MA544Tutorials H2036General Game Playing
12:30 - 14:00 Lunch
14:00 - 15:30 Workshops H3005Doctoral Consortium MA544Tutorials H2036General Game Playing
15:30 - 16:00 Coffee Break
16:00 - 17:30 Workshops H3005Doctoral Consortium MA544Tutorials H2036General Game Playing
17:30 - 18:30 H3005Panel: Bernhard Nebel (Universität Freiburg), Ingo Timm (Universität Trier),
Franz Baader (TU Dresden), Ulrich Frank (Universität Duisburg-Essen)
18:30 - 20:00 Exhibition, Welcome Reception (TU Hauptgebäude, Straße des 17. Juni 135, Lichthof)
Wednesday, Oct 5, 2011
08:30 - 18:00 Registration
09:00 - 10:30 H0104Keynote Speeches: Tag der Informatik
Peter Pepper, Stefan Jänichen, Constanze Kurz (CCC), Martin Schallbruch (IBM), Stephan Micklitz (Google)
10:30 - 11:00 Coffee Break
11:00 - 12:30 H1012Technical Papers 1: Probabilistic Inference and Combinatorial Search H1058Technical Papers 2: Computational Learning and Datamining
11:00 - 11:30 Paul Maier, Dominik Jain and Martin Sachenbacher. Compiling AI Engineering Models for Probabilistic Inference Matthias Reif, Faisal Shafait and Andreas Dengel. Prediction of Classifier Computation Time using Meta-Learning
11:30 - 12:00 Fabian Hadiji, Babak Ahmadi and Kristian Kersting. Efficient Sequential Clamping for Lifted Message Passing  Hamid Parvin. A New Criterion for Clusters Validation
12:00 - 12:30 Fabian Gieseke, Oliver Kramer, Antti Airola and Tapio Pahikkala. Speedy Local Search for Semi-Supervised Regularized Least-Squares  Dominik Endres, Andrea Christensen and Martin Giese. Segmentation of action streams: human observers vs. Bayesian binning
12:30 - 14:00 Lunch
14:00 - 15:30 H1012Technical Papers 3: Representation/Reasoning under Uncertainty H1058Technical Papers 4: Evolutionary and Neural Computation; Swarm Intelligence
14:00 - 14:30 Ruth Janning and Christoph Beierle. Transformation Rules for First-Order Probabilistic Conditional Logic Yielding Parametric Uniformity Michel Tokic and Günther Palm. Value-Difference based Exploration: Adaptive Control between epsilon-Greedy and Softmax
14:30 - 15:00 Dominik Jain, Klaus Von Gleissenthall and Michael Beetz. Bayesian Logic Networks and the Search for Samples with Backward Simulation and Abstract Constraint Learning Oliver Kramer and Fabian Gieseke. Variance Scaling for EDAs Revisited
15:00 - 15:30 Christoph Beierle, Marc Finthammer, Gabriele Kern-Isberner and Matthias Thimm. Evaluation and Comparison Criteria for Approaches to Probabilistic Relational Knowledge Representation Robert Haase, Hans-Joachim Böhme, Daniel Zips and Nasreddin Abolmaali. Swarm intelligence for medical volume segmentation: the contribution of self-reproduction
15:30 - 16:00 Coffee Break
16:00 - 18:00 H0104Keynote Speech: Luc Steels, ICREA/Institut de Biologia Evolutiva (UPF-CSIC) Barcelona; Sony CS Lab Paris
Powerful semantics can make language processing more robust
Keynote Speeches: Tag der Informatik
Manfred Broy (TU München), Danny Dolev (Hebrew University of Jerusalem)
   
20:00 - 23:00 Boat Banquet (ship leaves at "Haus der Kulturen der Welt"; bus transfer from TU is provided)
Thursday, Oct 6, 2011
08:30 - 18:00 Registration
09:30 - 10:30 H1012Keynote Speech: Michael Thielscher, University of New South Wales
General Game Playing in AI Research and Education
10:30 - 11:00 Coffee Break
11:00 - 12:30 H1012Technical Papers 5: Language and Vision H1058Technical Papers 6: Reasoning and Ontologies
11:00 - 11:30 Peter Adolphs, Feiyu Xu, Hans Uszkoreit and Hong Li. Dependency Graphs as a Generic Interface between Parsers and Relation Extraction Rule Learning Claus Zinn. Algorithmic Debugging To Support Cognitive Diagnosis in Tutoring Systems
11:30 - 12:00 Peter Adolphs, Anton Benz, Núria Bertomeu Castelló, Xiwen Cheng, Tina Klüwer, Manfred Krifka, Alexandra Strekalova, Hans Uszkoreit and Feiyu Xu. Conversational Agents in a Virtual World Martin Schmidt, Helmar Gust, Kai-Uwe Kühnberger and Ulf Krumnack. Refinements of Restricted Higher-Order Anti-Unification for Heuristic-Driven Theory Projection
12:00 - 12:30 Konrad Schenk, Markus Eisenbach, Alexander Kolarow and Horst-Michael Gross. Comparison of Laser-based Person Tracking at Feet and Upper-Body Height  Claudia Schon. Linkless Normal Form for ALC Concepts and Tboxes
12:30 - 14:00 Lunch
14:00 - 14:30 Martin Günther, Thomas Wiemann, Sven Albrecht and Joachim Hertzberg. Model-based object recognition from 3D laser data H105814:00 - 15:20      Short Paper Session 2: Learning
Nick Taubert, Dominik Endres, Andrea Christensen and Martin Giese. Shaking hands in latent space: modeling emotional interactions with Gaussian process latent variable models
14:30 - 15:30 H1012Short Paper Session 1: Vision and Speech
Albert Hein and Thomas Kirste. Generic Performance Metrics for continuous Activity Recognition
14:30 - 14:50 Daniel Oberhoff, Dominik Endres, Martin Giese and Marina Kolesnik. Gates for Handling Occlusion in Bayesian Models of Images
Jörn Hees, Benjamin Adrian, Thomas Roth-Berghofer and Andreas Dengel. Better Relations: Using a Game to Rate Linked Data Triples
14:50 - 15:10 Roland Roller, Tatjana Scheffler and Norbert Reithinger.
Human-Machine Corpus Analysis for Language Generation and Interaction with Spoken Dialog Systems
Marco Ragni and Andreas Klein. Predicting Numbers: An AI Approach to Solving Number Series
15:10 - 15:30 Martin Stommel. Classification of Semantical Concepts to Support the Analysis of the Inter-Cultural Visual Repertoires of TV News Reviews
   
15:30 - 16:00 Coffee Break
16:00 - 17:00 H1012Keynote Speech: Sven Koenig, University of Southern California
Making Good Decisions: Case Studies in Planning and Coordination
17:00 - 18:30 H2035Öffentliche Sitzung des Fachbereichs KI der Gesellschaft für Informatik
Friday, Oct 7, 2011
08:30 - 10:00 Registration
09:30 - 10:30 H1012Keynote Speech: Jörg Hoffmann INRIA, Nancy, France
Everything You Always Wanted to Know About Planning (But Were Afraid to Ask)
10:30 - 11:00 Coffee Break
11:00 - 12:30 H1012Technical Papers 9: Planning and Scheduling, Information Retrieval H1058Technical Papers 10: Augmented Reality/Smart World
11:00 - 11:30 Andrea Orlandini, Alberto Finzi, Amedeo Cesta and Simone Fratini. TGABased Controllers for Flexible Plan Execution Michal Matuszak, Jacek Miękisz and Tomasz Schreiber. Smooth Conditional Transition Paths in Dynamical Gaussian Networks
11:30 - 12:00 Felix Müller and Susanne Biundo. HTN-Style Planning in Relational POMDPs Using First-Order FSCs Björn Zenker and Alexander Münch. Calculating Meeting Points for Multi User Pedestrian Navigation Systems
12:00 - 12:30 Arne Schuldt. Shape Retrieval with Qualitative Relations: The Influence of Part-Order and Approximation Precision on Retrieval Performance and Computational Effort Jörg Lässig, Benjamin Satzger and Oliver Kramer. Hierarchically Structured Energy Markets as Novel Smart Grid Control Approach

Invited Speakers

Luc Steels

Powerful semantics can make language processing more robust

Human language is an inferential coding system which means that not all information to interpret an utterance is explicitly communicated, it must be inferred. Moreover the meaning of human language passes by intermediary of rich conceptualizations of the world which are culture and language dependent. These two features make natural language processing very difficult and introduce a glass ceiling for statistical language processing. This talk describes a computational framework for embodied cognitive semantics that is grounded in the sensori-motor intelligence of (humanoid) robots. We have used this in language game experiments that examine how open-ended robust language processing is possible by exploiting as much as possible meaning. Concrete examples are given of cognitive functions needed in conceptualization, the representation of spatial and temporal categories, the configuration of new conceptualization strategies by recruiting cognitive functions, and the mapping of conceptualization to language.

Luc Steels is professor of Computer Science (at the moment parttime) at the Free University of Brussels (VUB), founder and director (from 1983) of the VUB Artificial Intelligence Laboratory and co-founder and chairman (from 1990 until 1995) of the VUB Computer Science Department (Faculty of Sciences). Currently, he works at the ICREA/Institut de Biologia Evolutiva (UPF-CSIC) in Barcelona.

Luc Steel's scientific research interests cover the whole field of artificial intelligence, including natural language, vision, robot behavior, learning, cognitive architecture, and knowledge representation. At the moment his focus is on dialogs for humanoid robots and fundamental research into the origins of language and meaning. Current work focuses on developing the foundations of semiotic dynamics and on fluid construction grammars.
 

Jörg Hoffmann

Everything You Always Wanted to Know About Planning (But Were Afraid to Ask)

Domain-independent planning is one of the long-standing sub-areas of AI, aiming at approaching human problem-solving flexibility. The area has long had an affinity towards playful illustrative examples, imprinting it on the mind of many a student as an area concerned with the rearrangement of blocks, and with the order in which to put on socks and shoes (not to mention the disposal of bombs in toilets). Working on the assumption that this "student" is you - the audience in earlier stages of their careers - the talk aims to answer three questions that you surely desired to ask back then already: What is it good for? Does it work? Is it interesting to do research in? Answering the latter two questions in the affirmative (of course!), the talk outlines some of the major developments of the last decade, revolutionizing the ability of planning to scale up, and our understanding of the enabling technology. Answering the first question, the talk points out that modern planning proves to be quite useful for solving practical problems - including, perhaps, yours.

Joerg Hoffmann is a Directeur de Recherche at INRIA, Nancy, France. Before joining INRIA, he worked at the University of Freiburg (Germany), Max Planck Institute for Computer Science (Saarbruecken, Germany), the University of Innsbruck (Austria), and SAP Research (Karlsruhe, Germany). He is the recipient of several awards including the 2002 award for the best European dissertation in AI, and 3 best paper awards at international journals and conferences. He is an Associate Editor of the Journal of Artificial Intelligence Research, and a member of the Executive Council of the International Conference on Automated Planning and Scheduling.

Joerg's scientific interests concern the modeling, solution, and analysis of combinatorial search problems. His central area of research is AI Planning, but he has also worked on problems relating to SAT, Model Checking, and the Semantic Web. Most recently, he has developed a tool called "TorchLight", which one may imagine as a kind of fortune-teller for search performance in planning, and which Joerg hopes will eventually be able to replace himself in that role.
 

Sven Koenig

Making Good Decisions: Case Studies in Planning and Coordination

Intelligent systems (such as robots or decision-support systems) have to exhibit goal-directed behavior in real-time, even if they have only incomplete knowledge of their environment, imperfect abilities to manipulate it, limited or noisy perception or insufficient reasoning speed. Several research disciplines study how one can make good decisions, including artificial intelligence, theoretical computer science, operations research and economics. One can use ideas from these disciplines to build intelligent systems. I will present some examples from my research with a large number of collaborators and students to illustrate that one can often build even better systems when combining ideas from two or more of these disciplines.
The focus of this talk will be on replanning and auction-based coordination. Planning systems often need to replan quickly as their knowledge changes. Replanning from scratch is often very time consuming but incremental heuristic search methods can be used to speed it up. I will give an overview of recent advances on incremental heuristic search. Similarly, teams of agents often need to coordinate. Auctions in economics deal with competitive agents that often have long decision cycles, while auction-based coordination systems deal with cooperative agents that often have to operate in real-time. I will give an overview of recent advances on market mechanisms for the allocation of resources in cooperative domains. I will use examples from robotics as running examples throughout the talk.

Sven Koenig is a professor in computer science at the University of Southern California. He received a diploma in Computer Science (Specialization: Compiler Construction) from University of Hamburg in 1992 and a Ph.D. degree in computer science from Carnegie Mellon University for his dissertation on Goal-Directed Acting with Incomplete In- formation. He also holds M.S. degrees from the University of California at Berkeley and Carnegie Mellon University and is the recipient of an ACM Recognition of Service Award, an NSF CAREER award, an IBM Faculty Partnership Award, a Charles Lee Powell Foundation Award, a Raytheon Faculty Fellowship Award, a Mellon Mentoring Award, an SAIC Advisement Award, a Fulbright Fellowship and the Tong Leong Lim Pre- Doctoral Prize from the University of California at Berkeley. Most of his research centers around techniques for decision making (planning and learning) that enable single situated agents and teams of agents to act intelligently in their environments. Additional information on Sven can be found on his webpages: idm-lab.org.

Sven Koenig is interested in intelligent systems that have to operate in large, nondeterministic, nonstationary or only partially known domains. Most of my research centers around techniques for decision making (planning and learning) that enable single situated agents (such as robots or decision-support systems) and teams of agents to act intelligently in their environments and exhibit goal-directed behavior in real-time, even if they have only incomplete knowledge of their environment, imperfect abilities to manipulate it, limited or noisy perception or insufficient reasoning speed. Applications of his research include planetary exploration, supplychain management, medicine, crisis management (such as oil-spill containment), robotics and real-time games (entertainment, serious games, training and simulation).
 

Michael Thielscher

General Game Playing in AI Research and Education

Introduced through the first AAAI Competition in 2005 as a new AI Challenge, General Game Playing has quickly evolved into an established research topic in Artificial Intelligence. More recently it is also gaining popularity as a useful addition to AI curricula at universities around the world. The first part of this talk will survey the research landscape of General Game Playing. The second part will demonstrate General Game Playing to be both a valuable tool for teaching Logic, Logic Programming, Planning, Search and Decision Making, and a great motivator for students to design and implement their own AI systems.

Michael Thielscher is an ARC Future Fellow and a Professor at The University of New South Wales. He is also an Adjunct Professor with the School of Computing and Mathematics at the University of Western Sydney. He received his postgraduate diploma in 1992 and his Ph.D. in Computer Science in 1994, both with distinction, from Darmstadt University. He then joined Dresden University, where he was an associate professor before he moved to his present position. His Habilitation thesis was honoured with the Award for Research Excellence by the alumni of Darmstadt University in 1998, and in 2009 he won a Future Fellowship Award from the Australian Research Council.

Michael's current research is mainly in Knowledge Representation, Cognitive Agents and Robots, General Game Playing, and Constraint Logic Programming. He is author of over 100 refereed papers and four books, and he has co-authored the award-winning system FLUXPLAYER, which in 2006 was crowned the World Champion at the AAAI General Game Playing Competition.
 

Program of the Joint Doctoral Consortium (H 3005)

14:00 - 15:30 Session I

  • Introduction (René Schumann, HES-SO, Sierre)
  • Michael Baumann (University of Paderborn): Can Agents Learn to Control a Flock of Sheep? Learning in Massively Multi-Agent Systems
  • Radu-Casian Mihailescu (Rey Juan Carlos University): An organizational approach to agent-based smart grids via coalitional games
  • René Leistikow (University of Rostock): Self-organization and Cooperation Strategies for Device Ensembles in Smart Meeting Environments
  • Felix Rabe (Bielefeld University): Towards an Episodic Memory for an Virtual Agent
  • Michael Siebers (Otto-Friedrich-University, Bamberg): Combining Supervised and Unsupervised Learning. An Ensemble Learning Framework
15:30 - 16:00 Coffee Break

16:00 - 17:30 Session II

  • Jan Ole Berndt (TZI, Bremen) Self-organizing Multiagent Coordination
  • Kristina Yordanova (University of Rostock) Intention Recognition with the Help of Human Behaviour Models
  • Nico Potyka (Fern-Universität Hagen) Efficient algorithms for statistical learning
  • Andreas Scheuermann (University of Hohenheim) Semantic Technology for Intelligent Logistics Information Systems
Individual Discussions: Mentees and Mentors

17:30 - 18:30 Panel Discussion: Science and AI (H 3005)

Discussion with Bernhard Nebel (University of Freiburg), Ingo Timm (University of Trier), Franz Baader (TU Dresden), Ulrich Frank (University of Duisburg-Essen)

Best Paper Award

KI 2011 awards the price for the

Best Applied Paper 2011

to

Dominik Endres, Andrea Christensen, Lars Omlor, Martin A. Giese
for their work:
Segmentation of Action Streams. Human Observers vs. Bayesian Binning

and the price for the

Best Theoretical Paper 2011

to

Ruth Janning and Christoph Beierle
for their work:
Transformation Rules for First-Order Probabilistic Conditional Logic Yielding Parametric Uniformity

Call for Papers

KI 2011 is the 34th edition of the German Conference on Artificial Intelligence, which traditionally brings together academic and industrial researchers from all areas of AI. The technical programme of KI 2011 will comprise paper and poster presentations and a variety of workshops and tutorials.

KI 2011 will take place in Berlin, Germany, October 4-7, 2011, and is a premier forum for exchanging news and research results on theory and applications of intelligent system technology.

The applications of Artificial Intelligence are abundant and widespread. In fact, Artificial Intelligence has become such a mainstay in today's world that it is taken for granted by the majority of people who benefit from its efficiency. Therefore, the focus of the conference is on advances

"Towards a Smart World - Evolving Technologies in AI"

The conference invites original research papers from all areas of AI, its fundamentals, its algorithms, its history and its applications.

Areas of interest include, but are not limited to

  • Knowledge Acquisition, Representation, Reasoning and Ontologies,
  • Combinatorial Search, Configuration, Design and Deduction,
  • Natural Language Processing, Statistical NLP, Semantics,
  • Planning and Scheduling; Spatial and Temporal Reasoning,
  • Reasoning under Uncertainty, Probabilistic Inferences,
  • Non-Monotonic Reasoning and Default Logics,
  • Constraint Satisfaction, Processing and Programming,
  • Embodied AI: Robotics, Vision and Perception,
  • Intelligent Information Retrieval, Semantic Search, Semantic Web,
  • Evolutionary and Neural Computation,
  • Machine Learning, Computational Learning Theory and Data-Mining,
  • Distributed Problem Solving and Multi-Agent Systems,
  • Game Playing and Interactive Entertainment, AI for Graphics
  • Game Theory and General Game Playing, Generalized Intelligence,
  • AI for Human-Computer-Interaction and Adaptive Communication,
  • Mobile Solutions with Textile, Semantic and Spatial Media,
  • Augmented Reality, Smart Cities, Smart Traffic, Smart Hardware,
  • Assistance Systems in Living and Working Environments,
  • Software-Engineering, Model Checking and Security in AI,
  • Distributed Computation and Swarm Intelligence,
  • Artificial General Intelligence,
  • Cognitive Modelling, AI and Psychology,
  • History and Philosophical Foundations of AI,
  • Applications including Logistics, Production and Health Care

We especially welcome application papers providing novel insights on the interplay of AI and the real world, as well as papers that bring into AI useful computational technologies from other areas of computer science.


Submission Guidelines

Submitted papers, which have to be in English, must not exceed 12 pages in Springer LNCS style for full technical contributions and 4 pages for short contributions.

Full technical papers are expected to report on new research that makes a substantial technical contribution to the field and is placed in the context of existing work.

Short papers can report on new research or other issues of interest to the KI community. Examples of work suitable for short papers include: novel ideas that are not yet fully developed or whose scope is not large enough for a full paper; important implementation techniques; novel interesting benchmark problems; short experimental studies; interesting applications that are not yet completely solved or analyzed; position or challenge papers; etc.

Conference submission is electronic, in pdf or postscript format, available on

http://www.easychair.org/conferences/?conf=ki11

All papers will be reviewed based on the standard criteria of clarity, relevance, significance, originality, and soundness.

All accepted papers will be published in the main conference proceedings, and will be presented at the conference. The conference proceedings will be published in the Springer Lecture Notes in AI (LNAI) series. At least one author per accepted paper must register for the conference and present the contribution.

Call for Workshop and Tutorial Proposals

KI 2011, the 34th German Conference on Artificial Intelligence, invites original research papers, workshop and tutorial proposals from all areas of AI, its fundamentals and its applications.

Together with the main conference, we aim at organizing a small number of high-quality workshops and tutorials suitable for a large percentage of conference participants, including graduate students as well as experienced researchers and practitioners.

General Information

Workshops and tutorials will be free of charge for conference participants and will be held at the first and at the second day of the conference. Both full-day (6 hours) and half-day (3 hours) workshops and tutorials are of interest. They should preferably be given in English.
The KI 2011 conference organizers will provide logistic support and meeting places for the workshops as well as determine the dates and times of the workshops.
Working and teaching material will be printed by the conference organization. Volumes are limited to a total of 200 pages.

How to Propose a Workshop

Proposals should be prepared in PDF, or plain ASCII (two pages) and sent by email to the KI 2011 Workshop and Tutorial Chairs. Each workshop proposal should provide the following information:

  • Description of workshop topic and goal. This description should discuss the relevance of the suggested topic and its interest to the general AI community and the KI 2011 audience.
  • Names and full addresses (including email and web address) of the workshop organizer(s). This can be a single person or a group of persons. Please indicate the primary contact person for KI 2011. Strong proposals include organizers who bring differing perspectives to the workshop topic and who are actively connected to the communities of potential participants.
  • Names and affiliation of the members of the Program Committee.
  • For which areas of AI do you expect to draw participants for your workshop and how many participants do you expect? How do you plan to invite participants for the workshop?
  • A brief description of the workshop format regarding the mix of events such as paper presentation, invited talks, panels, demonstrations, and general discussion.
  • Do you expect the workshop to be a full-day workshop or a half-day workshop?

Workshop organizers will be responsible for:

  • Producing a call for participation. This call will be posted on the KI 2011 website.
  • Organizers are responsible for additional publicity such as distributing the call to relevant newsgroups and electronic mailing lists, and especially to potential audiences from outside the KI conference community.
  • Submissions of the workshop papers will be handled by the workshop organizers. Please make sure that you have a proper review process.
  • Organizers are encouraged to maintain their own web site with updated information about the workshop.
  • Coordinating the production of the workshop notes. The workshop organizer coordinates the paper collection, production and distribution of the working notes for the workshops.

How to Propose a Tutorial

Tutorials should give a comprehensive, in-depth perspective on innovative AI methods or technologies that have an obvious potential for research and/or application and are not covered by typical AI textbooks.

Do not hesitate to contact the Workshop and Tutorial Chairs if you are in doubt about the suitability of a particular topic for the purpose.

Proposal texts should be submitted by e-mail to the Workshop and Tutorial Chairs in pdf or plain text format. Annexes may be sent as .pdf, .ppt, or .doc format. Each tutorial proposal should provide the following information:

  • Descriptions of the tutorial topic, goals, the intended audience, an outline of the contents,
  • Necessary information to point out the importance, quality and community interest in the proposed tutorial.
  • Brief CVs of the tutor(s), including their expertise and teaching experience in the field,
  • The intended length of the tutorial (half- or full- day).

Proposers are encouraged to include excerpts of material from recent teaching about the proposed topic as an annex of their submission, if available.

Organizers are encouraged to support additional publicity such as distributing a tutorial abstract to relevant newsgroups and electronic mailing lists, and especially to potential audiences from outside the KI conference community. Organizers are encouraged to maintain their own web site with updated information about the tutorial.

Submission Guidelines

Submitted papers, which have to be in English, must not exceed 12 pages in Springer LNCS style for full technical contributions and 4 pages for short contributions.

Full technical papers are expected to report on new research that makes a substantial technical contribution to the field and is placed in the context of existing work.

Short papers can report on new research or other issues of interest to the KI community. Examples of work suitable for short papers include: novel ideas that are not yet fully developed or whose scope is not large enough for a full paper; important implementation techniques; novel interesting benchmark problems; short experimental studies; interesting applications that are not yet completely solved or analyzed; position or challenge papers; etc.

Conference submission is electronic, in pdf or postscript format, available on

http://www.easychair.org/conferences/?conf=ki11

Joint Doctoral Consortium KI & MATES 2011

Research in and applications of AI are widespread. In all the fields of research in AI scientists are working hard to achieve the vision this conference focuses on: a "smart world".

As the goal of the KI conference is to bring together researchers for an interesting exchange of ideas, it will attract PhD students, as well. These are especially addressed by the Doctoral Consortium (DC), which complements the program of talks, workshops and tutorials of the KI conference.

The goal of the DC is to support PhD students in all stages of their research in the field of AI. The DC wants to offer a platform for PhD students for presenting and discussing their results, ideas and planed work in a constructive atmosphere.

Moreover, each PhD student will be assigned to an experienced researcher who will act as a mentor and is going to provide detailed feedback and advice to help with their intended research. This often gives valuable external input and provides the opportunity to get in touch with different researchers to grow the personal academic network.

As a special feature of this year's DC we have organized a special discussion session. The topic of this session is to point out what good scientific practice in AI research really is, and what types of philosophy of science can be found in AI research. This session especially wants to reach out to doctorate students and wants to encourage a lively discussion. We have been able to invite several well established researchers to join us for this discussion. Our guests are:

  • Franz Baader (TU Dresden, Spokesperson DFG Review Board for Computer Science)
  • Ulrich Frank (University of Duisburg-Essen)
  • Bernhard Nebel (University of Freiburg, DFG-Review Board for AI)
  • Ingo Timm (University of Tier)

How to apply?

Please send the following documents via e-mail to schumann@nii.ac.jp:

1) A two-page abstract of your thesis, formatted following the KI guidelines, which describes research completed and plans for remaining work.

2) A CV (max 2 pages) that covers background (name, university, supervisor), education (degree sought, year/status in degree, previous degrees), employment, and relevant experience in research (e.g. publications, presentations, conferences attended, etc).

3) Research status (1 page) with a short research description in which you should provide answers to the following questions:
 a. Have you submitted (or will submit) a paper to the KI 2011 conference or co-located conferences? If yes, provide list of authors, title, and where submitted.
 b) Expected date of graduation
 c). Type of job (after completing your PhD) desired 
 This document will be used as an additional source of information for your assigned mentor.

Important Dates

Workshop Proposals: April 1, 2011 (expired)
Tutorial Proposals: April 1, 2011 (expired)
Application to Doctoral Consortium: July 8, 2011 (expired)

Paper Submission Deadline: May 1, 2011 (expired)
Notification: July 1, 2011 (expired)
Camera Ready: July 15, 2011 (expired)
Early Registration: July 31, 2011 (expired)

Venue

This year's annual German conference on AI will take place at and near the campus of Technical University Berlin.
TU Berlin has earned internationally acclaim for its excellence in research and and education. It is attended by 30.000 students, 3600 of these have enrolled in school of electrical engineering and computer sciences.
Together with Berlin's Humboldt-Universität and Freie Universität, several research institutes and many industry liaisons, the Technical University establishes Berlin as an important center of AI research, neural computation and cognitive robotics in Germany.

Campus Technical University

Accommodation

Berlin offers a large choice of hotels and hostels in every budget segment. We recommend to book early for best prices, though.

Accommodation near Ernst-Reuter-Platz
View Google Map

Conference Organization

  • General Chair: Stefan Edelkamp (Universität Bremen)
  • Local Chair: Joscha Bach (CILS, Berlin)
  • Workshop Chairs: Bernd Schattenberg (Universität Ulm)
  • Tutorial Chair: Sebastian Kupferschmid (Universität Freiburg)
  • Doctorial Consortium Chair: René Schumann (NII, Tokyo)
  • Industry Liaisons: Roman Englert (T-LABs)
  • Co-Location: Doris Fähndrich (TU Berlin)

Program Committee

Klaus-Dieter Althoff, Tamim Asfour, Joscha Bach, Amit Banerjee, Sven Behnke, Maren Bennewitz, Ralph Bergmann, Marc Cavazza, Daniel Cernea, Eliseo Clementini, Cristobal Curio, Kerstin Dautenhahn, Frank Dylla, Stefan Edelkamp, Dominik Endres, Florian Eyben, Udo Frese, Johannes Fuernkranz, Stefan Funke, Christopher Geib, Bjoern Gottfried, Horst-Michael Gross, Jens-Steffen Gutmann, Martin Günther, Fred Hamker, Malte Helmert, Dominik Henrich, Joachim Hertzberg, Otthein Herzog, Joerg Hoffmann, Gabriele Kern-Isberner, Peter Kissmann, Alexander Kleiner, Roman Kontchakov, Oliver Kramer, Ralf Krestel, Torsten Kroeger, Rudolf Kruse, Kai-Uwe Kühnberger, Bogdan Kwolek, Gerhard Lakemeyer, Tobias Lang, Hagen Langer, Volker Lohweg, Benedikt Lowe, Katja Markert, Robert Mattmüller, Bärbel Mertsching, Hartmut Messerschmidt, Bernd Michaelis, Ralf Moeller, Oliver Niggemann, Justus Piater, Felix Putze, Jochen Renz, Gerhard Rigoll, Alessandro Saffiotti, Juergen Sauer, Bernd Schattenberg, Malte Schilling, Ute Schmid, Lutz Schroeder, Carsten Schuermann, René Schumann, Jan-Georg Smaus, Luciano Spinello, Steffen Staab, Cyrill Stachniss, Rainer Stiefelhagen, Ingo Timm, Rudolph Triebel, Toby Walsh, Thomas Wiemann, Stefan Woelfl, Dirk Wollherr, Diedrich Wolter

Sponsors

KI 2011 offers opportunities to get in touch with leading researchers in the field of Artificial Intelligence.
Showcasing your own technology during the conference exihibition, and/or becoming a sponsor of KI 2011 is an opportunity to increase the visibility of your organization.


To learn more about sponsoring opportunities, please contact

Roman Englert, roman.englert@telekom.de

Download Conference Poster and Flyer

Conference Poster (1.8MB)
Info Flyer (720KB)

Contact

Conference organization

Stefan Edelkamp, edelkamp@tzi.de
TZI - Technologie-Zentrum Informatik und Informationstechnik
Universität Bremen
Postfach 33 04 40
28334 Bremen
Germany

Fon: +49-(0) 421 218-4676
Fax: +49-(0) 421 218-7820

Website

Joscha Bach, joscha.bach@gmail.com
Berlin School of Mind and Brain
Humboldt-Universität zu Berlin
Luisenstr. 50
10099 Berlin