Auflistung nach Autor:in "Michahelles, Florian"
1 - 7 von 7
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragEnhancing the Supervision of Out-of-View Robots: A Study on Multimodal Feedback and Monitoring Screens(Mensch und Computer 2023 - Tagungsband, 2023) Kassem, Khaled; Shahu, Ambika; Tüchler, Christina; Wintersberger, Philipp; Michahelles, FlorianObjective: investigating the effect of two support methods (multimodal feedback, monitoring screens, and a combination of both) on human dual-task performance, cognitive workload, and user experience when supervising an out-of-sight autonomous robot. Method: A 2x2 within-group user study was conducted in VR with 26 participants involving a cognitive-cognitive dual-task setting. Participants had to simultaneously solve math problems and supervise the robot. Different support methods were provided: multimodal feedback, a screen showing real-time robot activity, and a combination of both. Objective performance metrics and subjective feedback on cognitive load and user experience were collected using standard questionnaires. Data were statistically analyzed, and thematic analysis was performed on post-study debriefing interviews. Results: The support methods improved overall user experience and positively impacted robot collaboration performance while decreasing math task performance. Cognitive load was unaffected. Multimodal feedback with a monitoring screen was perceived as the most helpful. Conclusion: The results suggest that multimodal feedback can improve user experience and improve supervision, but may partially decrease primary task performance. The findings highlight the importance of examining the effect of support methods in specific situations, depending on task priority.
- KonferenzbeitragExplicit and implicit ratings for mobile applications(INFORMATIK 2010. Service Science – Neue Perspektiven für die Informatik. Band 1, 2010) Girardello, Andrea; Michahelles, FlorianToday most mobile operating systems provide an application portal (e.g. Android Market, A ppStore) where users can search by ke ywords and e xplicitly rate applications published by third-party developers. In this paper we go be yond this approach and introduce an implicit rating mechanism for Android programs. Our approach, c aptures installation, upd ate, a nd removal e vents, a nd allows to show them a mong us ers. B ased on these m easurements w e cal culate i mplicit ratings. As a result we compare these ratings with explicit ratings from the Android Market. For applications with less than 5,000 downloads implicit ratings provide more information than users explicitly enter on Android Market.
- WorkshopbeitragExploring Human-robot Interaction by Simulating Robots(Mensch und Computer 2022 - Workshopband, 2022) Kassem, Khaled; Michahelles, FlorianAs collaborative robots enter industrial shop floors, logistics, and manufacturing, rapid and flexible evaluation of human-machine interaction has become more important. The availability of consumer headsets for virtual and augmented realities has lowered the barrier of entry for virtual environments. In this paper, we explore the different aspects of using such environments for simulating robots in user studies and present the first findings from our own research work. Finally, we recommend directions for applying and using simulation in human-robot interaction.
- KonferenzbeitragHuman-machine Collaboration on Data Annotation of Images by Semi-automatic Labeling(Mensch und Computer 2021 - Tagungsband, 2021) Haider, Tom; Michahelles, FlorianDeployment of deep neural network architectures in computer vision applications requires labeled images which human workers create in a manual, cumbersome process of drawing bounding boxes and segmentation masks. In this work, we propose an image labeling companion that supports human workers to label images faster and more efficiently. Our data-pipeline utilizes One-Shot, Few-Shot and pre-trained object detection models to provide bounding box suggestions, thereby reducing the required user interactions during labeling to corrective adjustments. The resulting labels are then used to continuously update the underlying suggestion models. Optionally, we apply a refinement step, where an available bounding box is converted into a finer segmentation mask. We evaluate our approach with a group of participants who label images using our tool - both manually and with the system. In all our experiments, the achieved quality is consistently comparable with manually created labels at factor 2 to 6 faster execution times.
- WorkshopbeitragRobots for Public and Social Spaces - Design for Intent Communication, Collaboration and Acceptance(Mensch und Computer 2023 - Workshopband, 2023) Häkkilä, Jonna; Kassem, Khaled; Kirjavainen, Emma; Kraus, Johannes; Michahelles, Florian; Müller, Heiko; Pfleging, Bastian; Seyffer, Norman; Trost, Kai ErikIntent communication is crucial for human-robot interactions, allowing robots to understand and respond to human intentions and enabling humans to comprehend potentially autonomous robots’ intentions. Social robots have become increasingly popular in various fields, from healthcare to education, due to their ability to interact with humans naturally and intuitively. Enabling seamless communication between robots and humans is a key challenge in developing effective social robots. This workshop explores the intersection of intent communication and user experience in social robotics, with a focus on human-centered human-robot interaction.The workshop aims to bring together researchers, developers, and practitioners from academia and industry to discuss recent advances in intent communication and user experience design in social robotics. Participants can present their research, share experiences, and engage in interactive discussions with other attendees. The workshop provides a forum for collaboration and knowledge exchange to advance the state-of-the-art in social robotics and HRI. This is the second iteration of the RoboX workshop at MuC.
- KonferenzbeitragTowards an open product repository using playful crowdsourcing(INFORMATIK 2010. Service Science – Neue Perspektiven für die Informatik. Band 1, 2010) Budde, Andreas; Michahelles, FlorianDespite the ubiquity of barcodes there is no common product repository available today linking product master data to the corresponding barcodes. This paper proposes a social network game (Product Empire) that motivates users to scan barcodes and to enter basic product information, such as product name, brand and category and to upload a picture. A first prototype has been implemented and applied in an initial formative user study with 10 users who have generated 80 product scans with user-generated descriptions in a week time frame. This result shows the potential of generating an open product repository by motivating users with a game approach.
- WorkshopbeitragWorkshop on Intelligent Cyclist Support Systems and Applications(Mensch und Computer 2021 - Workshopband, 2021) von Sawitzky, Tamara; Wintersberger, Philipp; Matviienko, Andrii; Löcken, Andreas; Riener, Andreas; Michahelles, FlorianAlthough the number of cycling accidents increases, technology to improve traffic flow and safety was predominantly researched in the context of motor-powered vehicles in the past. While new assistance systems are being installed for driving safety in passenger cars, a similar development is lacking for bicycles. Although cycling support systems are slowly becoming an important research topic, there is still limited work addressing intelligent and collaborative applications for bikes. In this workshop, we will discuss and prototype potential intelligent support systems and their applications in the cycling domain. Our goal is to bring cycling and technology enthusiasts together to discuss and develop possible intelligent support systems that can enhance the cycling experience and make bikes a safer mode of transport.