Art der Publikation: Beitrag in Sammelwerk

Look Over Here! Comparing Interaction Methods for User-Assisted Remote Scene Reconstruction

Autor(en):

Liebers, Carina; Pfützenreuter, Niklas; Prochazka, Marvin; Megarajan, Pranav; Furuno, Eike; Löber, Jan; Stratmann, Tim C.; Auda, Jonas; Degraen, Donald; Gruenefeld, Uwe; Schneegass, Stefan

Titel des Sammelbands:

Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems

Verlag:

Association for Computing Machinery

Ort(e):

New York, NY, USA

Veröffentlichung:

2024

ISBN:

9798400703317

Schlagworte:

RGBD sampling, human-robot interaction, manual sampling, teleoperation, virtual reality

Digital Object Identifier (DOI):

doi:10.1145/3613905.3650982

Volltext:

Look Over Here! Comparing Interaction Methods for User-Assisted Remote Scene Reconstruction (6.58 MB)

Ergänzende Unterlagen:

(545 KB)

Zitation:

Download BibTeX

Kurzfassung

Detailed digital representations of physical scenes are key in many cases, such as historical site preservation or hazardous area inspection. To automate the capturing process, robots or drones mounted with sensors can algorithmically record the environment from different viewpoints. However, environmental complexities often lead to incomplete captures. We believe humans can support scene capture as their contextual understanding enables easy identification of missing areas and recording errors. Therefore, they need to perceive the recordings and suggest new sensor poses. In this work, we compare two human-centric approaches in Virtual Reality for scene reconstruction through the teleoperation of a remote robot arm, i.e., directly providing sensor poses (direct method) or specifying missing areas in the scans (indirect method). Our results show that directly providing sensor poses leads to higher efficiency and user experience. In future work, we aim to compare the quality of human assistance to automatic approaches.