SafeRelBench: VLM駆動身体化エージェントのプロセス安全性を評価する空間関係認識ベンチマーク
SafeRelBench: A Spatial-Relation-Aware Benchmark for Process-Level Safety in VLM-Driven Embodied Agents
VLM駆動の身体化エージェントの安全性を、物体の空間関係（支持・包含・近接）に着目して評価するベンチマークを提案し、タスク成功とプロセス安全性の乖離を明らかにした。
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: Huaigang Yang, Ya Li, Min Ren, Bo Dai, Zhenliang Zhang, Zhaofeng He
分類: cs.RO, cs.AI
原文アブストラクト
Vision-language models (VLMs) are increasingly used as the reasoning backbone of embodied agents, enabling robots to interpret visual scenes, follow language instructions, and plan multi-step actions. In household environments, however, safety depends not only on recognizing objects, but also on how actions change the physical scene over time. Existing embodied safety evaluations largely focus on static risk recognition, unsafe instruction refusal, or final-state task completion. As a result, process-level safety failures induced by spatial relations such as support, containment, and proximity remain insufficiently studied. To address this gap, we introduce SAFERELBENCH, a spatial-relation-aware safety benchmark with 507 executable evaluation samples, including 248 spatial-relation samples and 259 non-spatial control samples. Using SAFERELBENCH to evaluate seven open- and closed-source VLM-driven embodied agents, we find a substantial gap between task success and process-level safety compliance: models often complete the requested task while violating process-level safety constraints. Unlike prior benchmarks, SAFERELBENCH explicitly tests whether agents satisfy safety conditions before risk-prone actions, making spatial relations a core dimension in embodied safety assessment. More broadly, our results show that safe embodied intelligence requires not only stronger perception and planning, but also reliable reasoning about how object relations shape risk during interaction.
