Auflistung nach Autor:in "Schiller, Marvin"
1 - 2 von 2
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelDo It Yourself, but Not Alone: Companion-Technology for Home Improvement—Bringing a Planning-Based Interactive DIY Assistant to Life(KI - Künstliche Intelligenz: Vol. 35, No. 0, 2021) Bercher, Pascal; Behnke, Gregor; Kraus, Matthias; Schiller, Marvin; Manstetten, Dietrich; Dambier, Michael; Dorna, Michael; Minker, Wolfgang; Glimm, Birte; Biundo, SusanneWe report on the technology transfer project “Do it yourself, but not alone: Companion -Technology for Home Improvement” that was carried out by Ulm University in cooperation with Robert Bosch GmbH. We developed a prototypical assistance system that assists a Do It Yourself (DIY) handyman in carrying out DIY projects. The assistant, based on various AI and dialog management capabilities, generates a sequence of detailed instructions that users may just follow or adapt according to their individual preferences. It features explanation capabilities as well as pro-active support based on communication with the user as well as with the involved tools. We report on the project’s main achievements, including the findings of various empirical studies conducted in various development stages of the prototype.
- KonferenzbeitragEvaluating Knowledge-Based Assistance for DIY(Mensch und Computer 2018 - Workshopband, 2018) Schiller, Marvin; Behnke, Gregor; Bercher, Pascal; Kraus, Matthias; Dorna, Michael; Richter, Felix; Biundo, Susanne; Glimm, Birte; Minker, WolfgangWe report on the development of a companion system incorporating hierarchical planning, ontology-based knowledge modeling and multimodal cloud-based dialog. As an application scenario, we consider the domain of do-it-yourself (DIY) home improvement involving the use of power tools. To test and – if necessary – adjust the developed techniques, user studies are conducted throughout the development phase. We present fundamental considerations and open questions encountered when testing the implemented prototype with potential users and report first observations from a current study.