実環境におけるマルチロボットシステムの信頼と受容:EUプロジェクトBugWright2を例としたロードマップ
Trust and Acceptance of Multi-Robot Systems "in the Wild". A Roadmap exemplified within the EU-Project BugWright2
船舶検査・保守用の自律マルチロボットシステムを対象に、共有メンタルモデルの形成・更新を通じて信頼較正を最適化するためのロードマップを提案し、クロストレーニングやブリーフィング、適応型UIの役割を論じた。
著者: Pete Schroepfer, Nathalie Schauffel, Jan Gründling, Thomas Ellwart, Benjamin Weyers, Cédric Pradalier
分類: cs.RO, cs.HC
原文アブストラクト
This paper outlines a roadmap to effectively leverage shared mental models in multi-robot, multi-stakeholder scenarios, drawing on experiences from the BugWright2 project. The discussion centers on an autonomous multi-robot systems designed for ship inspection and maintenance. A significant challenge in the development and implementation of this system is the calibration of trust. To address this, the paper proposes that trust calibration can be managed and optimized through the creation and continual updating of shared and accurate mental models of the robots. Strategies to promote these mental models, including cross-training, briefings, debriefings, and task-specific elaboration and visualization, are examined. Additionally, the crucial role of an adaptable, distributed, and well-structured user interface (UI) is discussed.
