SPOC: 部分観測と物理制約下での安全を考慮した計画
SPOC: Safety-Aware Planning Under Partial Observability And Physical Constraints
部分観測や物理制約を考慮しつつ家庭内の危険を避ける安全志向の embodied タスク計画ベンチマーク SPOC を提案し、既存 LLM が安全な計画に苦戦することを示した。
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: Hyungmin Kim, Hobeom Jeon, Dohyung Kim, Minsu Jang, Jeahong Kim
分類: cs.RO
原文アブストラクト
Embodied Task Planning with large language models faces safety challenges in real-world environments, where partial observability and physical constraints must be respected. Existing benchmarks often overlook these critical factors, limiting their ability to evaluate both feasibility and safety. We introduce SPOC, a benchmark for safety-aware embodied task planning, which integrates strict partial observability, physical constraints, step-by-step planning, and goal-condition-based evaluation. Covering diverse household hazards such as fire, fluid, injury, object damage, and pollution, SPOC enables rigorous assessment through both state and constraint-based online metrics. Experiments with state-of-the-art LLMs reveal that current models struggle to ensure safety-aware planning, particularly under implicit constraints. Code and dataset are available at https://github.com/khm159/SPOC
