Auflistung nach:
Auflistung Künstliche Intelligenz 24(4) - November 2010 nach Titel
1 - 10 von 15
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelAdvances in Robot Programming by Demonstration(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Dillmann, Rüdiger; Asfour, Tamim; Do, Martin; Jäkel, Rainer; Kasper, Alexander; Azad, Pedram; Ude, Aleš; Schmidt-Rohr, Sven R.; Lösch, MartinRobot Programming by Demonstration (PbD) has been dealt with in the literature as a promising way to teach robots new skills in an intuitive way. In this paper we describe our current work in the field toward the implementation of PbD system which allows robots to learn continuously from human observation, build generalized representations of human demonstration and apply such representations to new situations.
- ZeitschriftenartikelApproaching Manual Intelligence(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Maycock, Jonathan; Dornbusch, Daniel; Elbrechter, Christof; Haschke, Robert; Schack, Thomas; Ritter, HelgeGrasping and manual interaction for robots so far has largely been approached with an emphasis on physics and control aspects. Given the richness of human manual interaction, we argue for the consideration of the wider field of “manual intelligence” as a perspective for manual action research that brings the cognitive nature of human manual skills to the foreground. We briefly sketch part of a research agenda along these lines, argue for the creation of a manual interaction database as an important cornerstone of such an agenda, and describe the manual interaction lab recently set up at CITEC to realize this goal and to connect the efforts of robotics and cognitive science researchers towards making progress for a more integrated understanding of manual intelligence.
- ZeitschriftenartikelAutomated Enactment Tracking for Dynamic Workflows(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Sauer, ThomasThe notion of workflows is an established concept to coordinate the activities within an organization. However, human workflow participants typically have to explicitly report the steps taken, limiting acceptance and effectiveness of workflow technology. In the presented PhD thesis, the novel approach of automated enactment tracking is introduced to overcome this problem. Using a Multi-Agent System, the data produced during everyday activities is evaluated in a robust and flexible manner. The system applies Case-Base Reasoning to identify the tasks performed, following the principle that similar tasks produce similar data. Agents further collaborate with each other to identify processes enacted in parallel, and to compensate for missing or inaccurate information.
- ZeitschriftenartikelCognition in Manual Assembly(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Stork, Sonja; Schubö, AnnaManual assembly conducted by skilled human workers is of outstanding relevance for flexible production with high precision. Nevertheless, due to capacity limitations humans need to be supported during the working process in order to reduce mental workload and for enhancement of performance. Cognitive technical systems are able to do so by adapting the process of production to the properties of human cognitive processes which are relevant in manual assembly. During manual assembly tasks workers are confronted with various sources of information and have to switch rapidly between different tasks. The complexity of task execution can be reduced by appropriate information presentation and planning of work steps. Firstly, information processing during the working process can be supported by attentional guidance while reducing search times and accelerating assembly execution. Secondly, as there exist many possible assembly sequences for one product the optimal order of single assembly steps has to be found and interferences from previous task steps have to be minimized. The article describes two scenarios for the investigation of attention allocation as well as for the investigation of task sequences and gives a summary of results achieved so far.
- ZeitschriftenartikelCognitive Interaction Technology(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Ritter, HelgeThe coming decade will bring raw processing power and storage capacities of everyday computers to the same level as small brains. Considering this, current interaction technology seems archaic as it still forces humans to follow highly stereotyped, narrow and often error-prone procedures in order to make computers, robots, or other machinery obey them. The vision behind the Excellence Cluster Cognitive Interaction Technology (CITEC) is to develop ways of interacting with technical systems that are as natural and smooth as communication between humans.
- ZeitschriftenartikelConstraint Based World Modeling for Multi Agent Systems in Dynamic Environments(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Göhring, DanielMobile autonomous robotics is a young and complex field of research. Since the world is uncertain and since robots can only gain partial information about it, probabilistic navigation algorithms became popular whenever a robot has to localize itself or surrounding objects. Furthermore, cooperative exploration and localization approaches have become very relevant lately, as robots begin to act not just alone but in groups. Within my thesis I analyze, how information can be exchanged between robots in order to improve their world model. Therefore I examine how communication of spatial percept-relations can help to improve the accuracy of the world model, in particular when the robots are poorly self-localized. First, percept-relations are being used to increase the modeling accuracy in static situations, later the approach is extended to moving objects. After focussing on suitable sensory data for communication, in the second part I present a Bayesian modeling approach, using constraint satisfaction techniques for complex belief functions. Constraint based localization methods will be analyzed in order to have a group of robots efficiently localized and to model their environment. The presented algorithms were implemented and tested within the RoboCup Standard Platform League (SPL).
- ZeitschriftenartikelCoTeSys—Cognition for Technical Systems(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Buss, Martin; Beetz, MichaelThe CoTeSys cluster of excellence (Beetz et al. in Proceedings of the 30th German Conference on Artificial Intelligence, KI-2007, pp. 19–42, 2007) investigates cognition for technical systems such as robots and factories. Cognitive technical systems (CTS) are information processing systems equipped with artificial sensors and actuators, integrated and embedded into physical systems, and acting in a physical world. They differ from other technical systems as they perform cognitive control and have cognitive capabilities. Cognitive control orchestrates reflexive and habitual behavior in accord with longterm intentions. Cognitive capabilities such as perception, action, knowledge and models, reasoning, learning and planning turn technical systems into systems that “know what they are doing”. The cognitive capabilities result in systems of higher reliability, flexibility, adaptivity and better performance.
- ZeitschriftenartikelInterview with Eric Berger (Co-Director, Personal Robotics Program, Willow Garage)(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Beetz, Michael; Kirsch, Alexandra
- ZeitschriftenartikelKI im Daten-Tsunami(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Bergmann, Ralph
- ZeitschriftenartikelLearning from Humans—Computational Models of Cognition-Enabled Control of Everyday Activity(KI - Künstliche Intelligenz: Vol. 24, No. 4, 2010) Beetz, Michael; Buss, Martin; Radig, BerndIn recent years, we have seen tremendous advances in the mechatronic, sensing and computational infrastructure of robots, enabling them to act in several application domains faster, stronger and more accurately than humans do. Yet, when it comes to accomplishing manipulation tasks in everyday settings, robots often do not even reach the sophistication and performance of young children. In this article, we describe an interdisciplinary research approach in which we design computational models for controlling robots performing everyday manipulation tasks inspired by the observation of human activities.