Logo des Repositoriums

Auflistung nach Autor:in "Neumann, Bernd"

1 - 5 von 5
  • Zeitschriftenartikel
    Aus den Turnschuhen
    (KI - Künstliche Intelligenz: Vol. 25, No. 4, 2011) Neumann, Bernd
  • Zeitschriftenartikel
    Bildverstehen und KI – der kleine Grenzverkehr
    (KI - Künstliche Intelligenz: Vol. 25, No. 4, 2011) Neumann, Bernd
  • Zeitschriftenartikel
    Künstliche Intelligenz - Perspektiven einer wissenschaftlichen Disziplin und Realisierungsmöglichkeiten
    (Informatik Spektrum: Vol. 14, No. 4, 1991) Barth, Gerhard; Christaller, Thomas; Cremers, Armin B.; Neumann, Bernd; Radermacher, Franz Josef; Radig, Bernd; Richter, Michael M.; Siekmann, Jörg H.; Seelen, Werner von
  • Zeitschriftenartikel
    Learning and Recognizing Structures in Façade Scenes (eTRIMS)—A Retrospective
    (KI - Künstliche Intelligenz: Vol. 24, No. 1, 2010) Hotz, Lothar; Neumann, Bernd
    Scene interpretation is the task of automatically creating descriptions for images. Such descriptions typically contain not only primitive objects but also structures that constitute primitive and structured objects. The learning and recognition of such structures was the objective of the EU project “eTraining for the Interpretation of Man-made Scenes (eTRIMS)”. The retrospective at hand presents main results of this project.
  • Zeitschriftenartikel
    The RACE Project
    (KI - Künstliche Intelligenz: Vol. 28, No. 4, 2014) Hertzberg, Joachim; Zhang, Jianwei; Zhang, Liwei; Rockel, Sebastian; Neumann, Bernd; Lehmann, Jos; Dubba, Krishna S. R.; Cohn, Anthony G.; Saffiotti, Alessandro; Pecora, Federico; Mansouri, Masoumeh; Konečný, Štefan; Günther, Martin; Stock, Sebastian; Lopes, Luis Seabra; Oliveira, Miguel; Lim, Gi Hyun; Kasaei, Hamidreza; Mokhtari, Vahid; Hotz, Lothar; Bohlken, Wilfried
    This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real robot task execution. Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system.