Auflistung nach:
Auflistung Künstliche Intelligenz 27(3) - August 2013 nach Erscheinungsdatum
1 - 10 von 14
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelAssistive Technology to Support the Mobility of Senior Citizens(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Schlieder, Christoph; Schmid, Ute; Munz, Michael; Stein, KlausMaintaining mobility despite the bodily, mental, or monetary challenges which often come along with advanced age is a relevant aspect of the quality of live. The collaborative research project EMN-Moves provides assistive technology for initiating and coordinating mobility support in residential districts. Mobility support is seen as a social task involving the interplay of housing societies, social organisations and residents of different age groups—with and without special needs. The project focuses on two aspects: (1) a Geo-Wiki for documenting temporary mobility barriers and for generating proposals for alternative routes, (2) a matchmaking service for bringing together (elderly) people who need support with volunteers.
- ZeitschriftenartikelStatistic Methods for Path-Planning Algorithms Comparison(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Muñoz, Pablo; Barrero, David F.; R-Moreno, María D.The path-planning problem for autonomous mobile robots has been addressed by classical search techniques such as A* or, more recently, Theta* or S-Theta*. However, research usually focuses on reducing the length of the path or the processing time. The common practice in the literature is to report the run-time/length of the algorithm with means and, sometimes, some dispersion measure. However, this practice has several drawbacks, mainly due to the loose of valuable information that this reporting practice involves such as asymmetries in the run-time, or the shape of its distribution. Run-time analysis is a type of empirical tool that studies the time consumed by running an algorithm. This paper is an attempt to bring this tool to the path-planning community. To this end the paper reports an analysis of the run-time of the path-planning algorithms with a variety of problems of different degrees of complexity, indoors, outdoors and Mars surfaces. We conclude that the time required by these algorithms follows a lognormal distribution.
- ZeitschriftenartikelAttention-Based Detection of Unknown Objects in a Situated Vision Framework(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Martín García, Germán; Frintrop, Simone; Cremers, Armin B.We present an attention-based approach for the detection of unknown objects in a 3D environment. The ability to address individual objects in the environment without having previous knowledge about their properties or their identity is one important requirement of the Situated Vision theory. Based on saliency maps, our attention system determines the regions where objects are likely to be found; these are the proto-objects whose extent is refined by a 2D segmentation step. At the same time a 3D scene model is built from measurements of a depth camera. The detected objects are projected into the 3D scene, resulting in 3D object models which are incrementally updated. We show the validity of our approach in an RGB-D sequence recorded in an office environment.
- ZeitschriftenartikelLeuchttürme und Durchlauferhitzer(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Hertzberg, Joachim
- ZeitschriftenartikelEchtzeit-Videoanalyse im Fußball(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Schlipsing, Marc; Salmen, Jan; Igel, ChristianDie Automatisierung der Videoanalyse nimmt im Profisport eine immer wichtigere Rolle ein. Im Fußball kommt dabei der Auswertung der Laufwege der Spieler eine besondere Bedeutung zu. Der vorliegende Bericht dokumentiert unser Kooperationsprojekt zum computergestützten Spieler-Tracking auf Basis von Videobildern in Echtzeit. Wir beschreiben den Aufbau und diskutieren die Praxistauglichkeit des entwickelten Systems, das sich durch hohe Genauigkeit, Mobilität und Kostengünstigkeit auszeichnet.
- ZeitschriftenartikelTowards Automation of Simulation Studies(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Lattner, Andreas D.Simulation is applied in various domains to investigate different variants, to study effects, or to optimize models with respect to some performance measurement. Simulation models can exhibit a high level of complexity and thus, consist of many components and potentially many adjustable input parameters as well as a large number of output measurements. In this habilitation thesis, different methods in the fields of automation, data mining, and optimization in the context of simulation are developed. The underlying motivation is to increase the degree of automation and to increase the efficiency when performing simulation studies. The proposed methods are evaluated using three different simulation systems: Manufacturing simulation, traffic simulation, and gas dispersion simulation.
- ZeitschriftenartikelA Multi-objective Genetic Algorithm for Build Order Optimization in StarCraft II(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Köstler, Harald; Gmeiner, BjörnThis article presents a modified version of the multi-objective genetic algorithm NSGA II in order to find optimal opening strategies in the real-time strategy game StarCraft II. Based on an event-driven simulator capable of performing an accurate estimate of in-game build-times the quality of different build lists can be judged. These build lists are used as chromosomes within the genetic algorithm. Procedural constraints e.g. given by the Tech-Tree or other game mechanisms, are implicitly encoded into them. Typical goals are to find the build list producing most units of one or more certain types up to a certain time (Rush) or to produce one unit as early as possible (Tech-Push). Here, the number of entries in a build list varies and the objective values have in contrast to the search space a very small diversity. We introduce our game simulator including its graphical user interface, the modifications necessary to fit the genetic algorithm to our problem, test our algorithm on different Tech-Pushes and Rushes for all three races, and validate it with empirical data of expert StarCraft II players.
- ZeitschriftenartikelFrom Supervised to Unsupervised Support Vector Machines and Applications in Astronomy(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Gieseke, FabianSupport vector machines are among the most popular techniques in machine learning. Given sufficient labeled data, they often yield excellent results. However, for a variety of real-world tasks, the acquisition of sufficient labeled data can be very time-consuming; unlabeled data, on the other hand, can often be obtained easily in huge quantities. Semi-supervised support vector machines try to take advantage of these additional unlabeled patterns and have been successfully applied in this context. However, they induce a hard combinatorial optimization problem. In this work, we present two optimization strategies that address this task and evaluate the potential of the resulting implementations on real-world data sets, including an example from the field of astronomy.
- ZeitschriftenartikelReinforcement Learning: Psychologische und neurobiologische Aspekte(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Tokic, MichelMathematische Modelle von neurobiologisch und psychologisch inspirierten Lernparadigmen gelten als Schlüsseltechnologie für Problemstellungen, die anhand klassischer Programmierung schwer zu lösen sind. Reinforcement Learning ist in diesem Zusammenhang eines dieser Paradigmen, welches mittlerweile recht erfolgreich in der Praxis eingesetzt wird (u. a. in der Robotik), um Verhalten durch Versuch und Irrtum zu erlernen. In diesem Artikel möchte ich etwas näher auf die in Zusammenhang stehenden neurobiologischen und psychologischen Aspekte eingehen, welche das Vorbild einer Vielzahl mathematischer Modelle sind. Gesamtheitlich betrachtet ist Reinforcement Learning nicht ausschließlich für Lernen im Gehirn von Menschen und Tieren verantwortlich. Stattdessen findet ein großartiges Zusammenspiel mehrerer Paradigmen aus unterschiedlichen Hirnarealen statt, bei welchem auch Supervised- und Unsupervised Learning beteiligt sind.
- ZeitschriftenartikelNews(KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013)