視覚言語モデルはロボットの一人称画像から近接リスクを評価できるか?
Can Vision-Language Models Assess Proxemic Risk from Egocentric Robot Images?
ロボットの一人称視点画像を4段階の危険度に分類する際、3つの視覚言語モデルの性能を評価し、ファインチューニングやプロンプト戦略の効果を検証した。高危険度の検出には一部モデルで改善が見られたが、空間的根拠付けは不十分だった。
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: Vladyslava Rudas, Dmytro Kuzmenko
分類: cs.CV, cs.RO
原文アブストラクト
Assessing proxemic danger from a robot's egocentric perspective is critical for safe embodied navigation in human environments and requires both visual and contextual reasoning. We evaluate three opensource vision-language models (VLMs) (\textit{InternVL}, \textit{Qwen-VL}, and \textit{SmolVLM}) on the classification of egocentric robot images into four danger levels, comparing three prompting strategies and two rounds of QLoRA fine-tuning against a stratified random baseline. Without fine-tuning, all models perform near the baseline, while fine-tuning yields only modest overall improvements. However, \textit{Qwen-VL} with an advanced prompt achieves substantially higher recall for high-danger cases than the other models. An analysis of person localization further shows that correct danger classification does not correspond to better spatial grounding, indicating that a model may produce a useful safety label without attending to the relevant region of the scene. These results show that current VLMs remain limited in fine-grained proxemic reasoning and spatial grounding, although targeted prompting and fine-tuning can improve high-danger detection in selected models.