指差し誘導による対象推定:Transformerベースの注意機構を用いて
Pointing-Guided Target Estimation via Transformer-Based Attention
人間の指差しジェスチャーからテーブル上の対象物を推定するため、モダリティ間注意機構を活用したモジュール型アーキテクチャMM-ITFを提案し、単眼RGB画像で高精度に対象を予測できることを示した。
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: Luca Müller, Hassan Ali, Philipp Allgeuer, Lukáš Gajdošech, Stefan Wermter
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
Deictic gestures, like pointing, are a fundamental form of non-verbal communication, enabling humans to direct attention to specific objects or locations. This capability is essential in Human-Robot Interaction (HRI), where robots should be able to predict human intent and anticipate appropriate responses. In this work, we propose the Multi-Modality Inter-TransFormer (MM-ITF), a modular architecture to predict objects in a controlled tabletop scenario with the NICOL robot, where humans indicate targets through natural pointing gestures. Leveraging inter-modality attention, MM-ITF maps 2D pointing gestures to object locations, assigns a likelihood score to each, and identifies the most likely target. Our results demonstrate that the method can accurately predict the intended object using monocular RGB data, thus enabling intuitive and accessible human-robot collaboration. To evaluate the performance, we introduce a patch confusion matrix, providing insights into the model's predictions across candidate object locations. Code available at: https://github.com/lucamuellercode/MMITF.
