都市捜索における地上ロボット群の活用：専門家の運用課題と設計機会の理解
Applying Ground Robot Fleets in Urban Search: Understanding Professionals' Operational Challenges and Design Opportunities
バージニア州の警察官8名へのフォーカスグループ調査を通じ、地上ロボット群が都市捜索の認知・身体的負担を軽減しうる4つの課題領域と、将来の導入に向けた4つの設計機会を明らかにした。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Puqi Zhou, Charles R. Twardy, Cynthia Lum, Myeong Lee, David J. Porfirio, Michael R. Hieb, Chris Thomas, Xuesu Xiao, Sungsoo Ray Hong
分類: cs.HC, cs.RO
原文アブストラクト
Urban searches demand rapid, defensible decisions and sustained physical effort under high cognitive and situational load. Incident commanders must plan, coordinate, and document time-critical operations, while field searchers execute evolving tasks in uncertain environments. With recent advances in technology, ground-robot fleets paired with computer-vision-based situational awareness and LLM-powered interfaces offer the potential to ease these operational burdens. However, no dedicated studies have examined how public safety professionals perceive such technologies or envision their integration into existing practices, risking building technically sophisticated yet impractical solutions. To address this gap, we conducted focus-group sessions with eight police officers across five local departments in Virginia. Our findings show that ground robots could reduce professionals' reliance on paper references, mental calculations, and ad-hoc coordination, alleviating cognitive and physical strain in four key challenge areas: (1) partitioning the workforce across multiple search hypotheses, (2) retaining group awareness and situational awareness, (3) building route planning that fits the lost-person profile, and (4) managing cognitive and physical fatigue under uncertainty. We further identify four design opportunities and requirements for future ground-robot fleet integration in public-safety operations: (1) scalable multi-robot planning and control interfaces, (2) agency-specific route optimization, (3) real-time replanning informed by debrief updates, and (4) vision-assisted cueing that preserves operational trust while reducing cognitive workload. We conclude with design implications for deployable, accountable, and human-centered urban-search support systems
