Logo des Repositoriums

Auflistung nach Autor:in "Kopp, Stefan"

1 - 6 von 6
  • Zeitschriftenartikel
    Co-constructing Grounded Symbols—Feedback and Incremental Adaptation in Human–Agent Dialogue
    (KI - Künstliche Intelligenz: Vol. 27, No. 2, 2013) Buschmeier, Hendrik; Kopp, Stefan
    Grounding in dialogue concerns the question of how the gap between the individual symbol systems of interlocutors can be bridged so that mutual understanding is possible. This problem is highly relevant to human–agent interaction where mis- or non-understanding is common. We argue that humans minimise this gap by collaboratively and iteratively creating a shared conceptualisation that serves as a basis for negotiating symbol meaning. We then present a computational model that enables an artificial conversational agent to estimate the user’s mental state (in terms of contact, perception, understanding, acceptance, agreement and based upon his or her feedback signals) and use this information to incrementally adapt its ongoing communicative actions to the user’s needs. These basic abilities are important to reduce friction in the iterative coordination process of co-constructing grounded symbols in dialogue.
  • Konferenzbeitrag
    A conversational virtual human as autonomous assistant for elderly and cognitively impaired users? Social acceptability and design considerations
    (INFORMATIK 2013 – Informatik angepasst an Mensch, Organisation und Umwelt, 2013) Kramer, Marcel; Yaghoubzadeh, Ramin; Kopp, Stefan; Pitsch, Karola
    In this paper we explore how a conversational virtual human could be designed to be deployed as a socially acceptable autonomous assistive system for elderly and cognitively impaired users. In particular, we focus on a system's functionality in helping to maintain a well-structured daily life. We present initial findings from two types of studies: (1) Conducting interviews and focus groups considering users' attitudes and design considerations for assistance in maintaining well-structured daily routines and (2) analyzing interaction between the system and its users' while entering data into a calendar application. Analysis has revealed a set of design considerations for developing a socially acceptable system. Microanalytic investigation of one user's concrete interaction with a Wizard-of-Oz version of the system has shown that a cognitively impaired person is able - by himself and only through interacting with the system - to gain insights into the system's possibilities and limits and to mistrust the system's competencies once the system initiates a repair sequence.
  • Konferenzbeitrag
    Interactive Human-Guided Optimization for Logistics Planning
    (Mensch und Computer 2015 – Proceedings, 2015) Mattar, Nikita; Kulms, Philipp; Kopp, Stefan
    Logistics planning is an important problem in industry, where goods have to be parceled appropriately to meet delivery dates or reduce shipping costs. This optimization problem is classically solved offline using standard algorithms and focused heuristics, e.g. bin packing or route planning. However, in practical work environments, constraints may change flexibly and it is often not clear what an optimal solution looks like. Further, logistics planning consists of multiple steps that often are handled by different human employees in different departments. In this paper we propose an interactive approach using human-guided optimization, where solution spaces can be interactively explored, manipulated, and constrained at runtime. Based on an analysis of the problem of multi-step logistics planning, we present a system that supports users in solving this optimization problem, and we report first evaluation results obtained in the first two iterations of a user-centered design process.
  • Konferenzbeitrag
    More human-likeness, more trust? The effect of anthropomorphism on self-reported and behavioral trust in continued and interdependent human-agent cooperation
    (Mensch und Computer 2019 - Tagungsband, 2019) Kulms, Philipp; Kopp, Stefan
    Computer agents are increasingly endowed with anthropomorphic characteristics and autonomous behavior to improve their capabilities for problem-solving and make interactions with humans more natural. This poses new challenges for human users who need to make trust-based decisions in dynamic and complex environments. It remains unclear if people trust agents like other humans and thus apply the same social rules to human-computer interaction (HCI), or rather, if interactions with computers are characterized by idiosyncratic attributions and responses. To this ongoing and crucial debate we contribute an experiment on the impact of anthropomorphic cues on trust and trust-related attributions in a cooperative human-agent setting, permitting the investigation of interdependent, continued, and coordinated decision-making toward a joint goal. Our results reveal an incongruence between self-reported and behavioral trust measures. First, the varying degree of agent anthropomorphism (computer vs. virtual vs. human agent) did not affect people's decision to behaviorally trust the agent by adopting task-specific advice. Behavioral trust was affected by advice quality only. Second, subjective ratings indicate that anthropomorphism did increase self-reported trust.
  • Konferenzbeitrag
    Multimodale Interaktion in der Virtuellen Realität
    (Mensch & Computer 2001: 1. Fachübergreifende Konferenz, 2001) Wachsmuth, Ipke; Voss, Ian; Sowa, Timo; Latoschik, Marc E.; Kopp, Stefan; Jung, Bernhard
    Virtuelle Realität oder Virtual Reality (VR) bezeichnet ein neuartiges Kommunikationsmedium, das die unmittelbare Wechselwirkung des Menschen mit räumlich organisierten rechnergenerierten Darstellungen erlaubt. Verbunden mit körperlich verankerter Interaktion finden insbesondere gestische Eingaben starkes Interesse. Dieser Beitrag gibt einen Überblick über Forschungsarbeiten im Labor für Künstliche Intelligenz und Virtuelle Realität an der Universität Bielefeld, mit denen Grundlagen für den Einsatz gestischer und sprachlicher Interaktionstechniken entwickelt werden; als Erprobungsdomäne dient ein Szenario des virtuellen Konstruierens. Für die schnelle Erfassung komplexer Hand-Armgesten werden derzeit Datenhandschuhe und Körper-Tracker eingesetzt. Die Auswertung erfolgt mit wissensbasierten Ansätzen, die atomare Formelemente der Gestik symbolisch beschreiben und zu größeren Einheiten zusammensetzen. Ein zweites Thema ist die multimodale Interaktion durch sprachlich-gestische Eingaben, z.B. wenn auf einen Gegenstand gezeigt („dieses Rohr“) oder eine Drehrichtung („so herum“) signalisiert wird. Schließlich wird dargestellt, wie die Ansätze zur Formbeschreibung von Gesten für die Synthese natürlich wirkender gestischer Ausgaben mit einer artikulierten, anthropomorphen Figur übertragen werden können, die in laufenden Arbeiten mit Sprachausgaben koordiniert werden.
  • Konferenzbeitrag
    MultiPro: Prototyping Multimodal UI with Anthropomorphic Agents
    (Mensch und Computer 2018 - Tagungsband, 2018) Kulms, Philipp; van Welbergen, Herwin; Kopp, Stefan
    Modern user interfaces (UI) often provide natural and multimodal interaction, sometimes modelled in the form of a conversation with an anthropomorphic agent embedded in the system. Designing such interfac-es is a challenging task. Furthermore, it is often not clear which user scenarios will profit from a social, conversational interaction paradigm and how it could be integrated with classic paradigms like direct manipulation interfaces. Our multimodal prototyping framework MultiPro helps designers in rapidly designing UIs to explore these questions. It allows the easy prototyping and evaluation of UI using a mix of anthropomorphic (e.g., human-like appearance, speech) and classic graphical elements. We illustrate how designers can specify the look and interaction flow with MultiPro, how MultiPro supports user-based evaluation of the designs, and how MultiPro is used in HCI research applications.