KI - Künstliche Intelligenz

German Journal on Artificial Intelligence - Organ des Fachbereichs "Künstliche Intelligenz" der Gesellschaft für Informatik e.V.

ISSN: 0933-1875 (Print) 1610-1987 (Online)


The Scientific journal "KI – Künstliche Intelligenz" is the official journal of the division for artificial intelligence within the "Gesellschaft für Informatik e.V." (GI) – the German Informatics Society – with contributions from throughout the field of artificial intelligence. The journal presents all relevant aspects of artificial intelligence – the fundamentals and tools, their use and adaptation for scientific purposes, and applications which are implemented using AI methods – and thus provides the reader with the latest developments in and well-founded background information on all relevant aspects of artificial intelligence. For all members of the AI community the journal provides quick access to current topics in the field and promotes vital interdisciplinary interchange.


20 Years of RoboCup

The interaction of interdisciplinary topics is a scientific goal always. This applies in particular to the AI and robotics. Once you have decades more or less side by side research, there are at least since the introduction of the RoboCup 1997, a new type of collaboration between the two research directions.

RoboCup promotes joint research in the field of AI and robotics, while also providing even "hands-on science". At the annual competitions conducted to measure approximately 1,500 researchers and 1.000 high school students from about 40 countries. In the areas of "soccer, rescue scenarios, home and junior" latest developments are presented during competitions.

The German Journal on Artificial Intelligence is publishing a Special Issue on the topic "20 Years of RoboCup". RoboCup clearly is a success story. 10 years after the first German RoboCup, RoboCup is coming back to Germany again. With some 30 years to go until 2050, it is a good point in time to have a look at the technical achievements but also the impact of RoboCup, to the research community, education, and industry.

The topics of interest include, but are not limited to:

Perception and Action: 3D perception, distributed sensor integration, sensor noise filtering, real-time image processing and pattern recognition, motion and sensor models, sensory-motor control, robot kinematics and dynamics, high-dimensional motion control.
Robot Cognition and Learning: world modeling and knowledge representation, learning from demonstration and imitation, localization, navigation, and mapping, planning and reasoning, decision making under uncertainty, reinforcement learning, complex motor skill acquisition, motion and sensor model learning.
Multi-Robot Systems: team coordination methods, communication protocols, learning and adaptive systems, teamwork and heterogeneous agents, dynamic resource allocation, adjustable autonomy.
Human-Robot Interaction: human-robot interfaces, speech synthesis and natural language generation, visualization, emotion recognition, understanding human intent, affect detection and synthesis, robot response to external disturbances, safety and dependability.
Education and Edutainment: robotics and artifcial intelligence education, educational robotics, robot kits and programming tools, robotic entertainment.
Applications and Benchmarking: search and rescue robots, robotic surveillance, service and social robots, robots at home, performance metrics.
Robot Hardware and Software: mobile robotics, humanoid robotics, sensors and actuators, embedded and mobile devices, robot construction and new materials, robotic system integration, robot software architectures, robot programming environments and languages, real-time and concurrent programming, robot simulators.

Important dates:
Submission of papers: April 30, 2016
Notification to authors: May 15, 2016
Submission of camera-ready copies: May 31, 2016

The Künstliche Intelligenz journal, which is published and indexed by Springer, supports the following lists of formats for this special issue: Technical contributions (6-10 pages), research projects (4 pages), discussions, dissertation abstracts, conference reports and book reviews. If you are interested in contributing to this special issue, please contact one of the guest editors. Please signal your interest in submitting a paper by sending a working title of your manuscript to the guest editors in advance.

Dr. Gerald Steinbauer
Institute for Software Technology
Technische Universität Graz
Inffeldgasse 16b/2, A-8010 Graz, Austria

Prof. Dr. Alexander Ferrein
Fachhochschule Aachen
FB Elektrotechnik und Informationstechnologie
Eupener Strasse 70
52066 Aachen

Challenges for Reasoning Under Uncertainty, Inconsistency, Vagueness, and Preferences

Managing uncertainty, inconsistency, vagueness, and preferences has been extensively explored in Artificial Intelligence. During the recent years, especially with the emerging of smart services and devices, technologies for managing uncertainty, inconsistency, vagueness, and preferences to tackle the problems of dynamic, real-world scenarios have started to play a key role also in other areas, such as information systems and the (Social or Semantic) Web. These application areas have sparked another wave of strong interest into formalisms and logics for dealing with uncertainty, inconsistency, vagueness, and preferences. Important examples are fuzzy and probabilistic approaches for description logics, or rule systems for handling vagueness and uncertainty in the Semantic Web, or formalisms for handling user preferences in the context of ontological knowledge in the Social Semantic Web. While scalability of these approaches is an important issue to be addressed, also the need for combining various of these approaches with each other or more classical ways of reasoning have become obvious (hybrid reasoning under uncertainty).

The aim of the special issue is to collect overview articles on important state-of-the-art formalisms and methodologies, as well as articles on emerging trends for the future.

Prof. Gabriele Kern-Isberner
TU Dortmund
Fakultät für Informatik

Prof. Thomas Lukasiewicz
Professor of Computer Science
University of Oxford

Landmark-Based Navigation in Cognitive Systems

The importance of landmarks in human navigation has long been recognized in multiple fields. These include areas involved in the understanding, modelling and supporting wayfinding, spatial knowledge acquisition, and place recognition. From the Psychological, Linguistic and Cognitive Neuroscience viewpoint, the perceived landmarkness of discrete objects vary among individuals. Thus, the key challenge lies in identifying those properties, which remain relevant across a wide range of individual differences, experiences, and behavioural patterns. From the Computer Science, Artificial Intelligence and Cognitive Modelling perspective, formalising these relations in a manner successfully matching the landmark’s relevance for humans has proven difficult. Most recently, the increasing volume and accessibility of semantically rich geospatial data has opened new avenues for further progress in this area. The continuing collaboration between these fields is exemplified by the regular conference series on spatial information theory and geospatial science as well as multiple on-going interdisciplinary research projects.
In spite of that, technologies used to support human navigation struggle to incorporate the type of landmark information relevant for the human user. The gap between the human’s and the computer’s understanding of what constitutes a landmark remains one of the major challenges in the development of spatial systems intuitive in use as well as in modelling navigational behaviour similar to this of a human.
This special issue integrates theoretical, experimental and computational contributions from disciplines involved in the study of landmark-based navigation in cognitive systems. The aim of the issue is to identify new areas for potential interdisciplinary collaboration and we invite applications focusing on, but not limited to, the following topics:
– Automatic, semi-automatic, and crowd-sourced detection of landmarks.
– Modelling of landmark-based navigation.
– Landmark knowledge acquisition and use.
– Communication of landmark-ness.
– Landmark-based approaches for indoor navigation.
– Human-computer interaction with landmark-based systems.
– Ubiquitous computing applications of the landmark concept.

The KI Journal, which is published and indexed by Springer, supports the following lists of formats: Technical contributions, research projects, discussions, dissertation abstracts, conference reports, software, and book reviews. If you are interested in contributing to this special issue, please contact one of the guest editors:
Prof. Dr. Angela Schwering
Dr. Jakub Krukar
Vanessa Joy Anacta

Institute for Geoinformatics
University of Muenster
D-48149 Muenster

Browse Volumes & Issues