Finder: 身体性グラウンディングのためのエージェント型閉ループ物体探索
Finder: Agentic Closed-Loop Object Finding for Embodied Grounding
言語で指定された物体を部分的に観測された3Dシーンから見つけるため、計画・証拠収集・検証・制御を閉ループで回すエージェント型手法を提案し、物体検索や質問応答で精度を向上させた。
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: Shixiong Xu, Zhiyuan Chen, Song Ding, Rui Luo, Xiaowei Liang, Dongxu Miao, Zhiying Du
分類: cs.CV
原文アブストラクト
Finding the object referred to by language in a partially observed 3D scene is a core capability for embodied agents. Existing approaches either couple object search with online exploration, which can be costly when relevant observations have already been captured, or query pre-built open-vocabulary maps and scene graphs in a static, one-shot fashion. We present Finder, an agentic closed-loop object-finding primitive for embodied grounding. Instead of treating grounding as passive retrieval from a fixed scene representation, Finder maintains a typed loop state that links query-conditioned planning, scoped evidence gathering, candidate verification, and accept/continue/abort control. When evidence is incomplete or ambiguous, the loop can redirect subsequent perception and comparison rather than simply returning the top retrieved object. On open-vocabulary embodied Object Retrieval in Habitat/HM3D and real-world RGB-D scenes, Finder improves the averaged 1m success rate by 15.75 points over strong baselines. The same primitive also transfers to sequential object grounding and embodied object-centric question answering, improving spatial and temporal localization without changing the inner grounding protocol. Project page: https://finder-vln.github.io.