Kinaema: 移動中の記憶と姿勢のための再帰シーケンスモデル
Kinaema: a recurrent sequence model for memory and pose in motion
移動しながら視覚観測を再帰的に圧縮して暗黙の記憶を保持し、クエリ画像の相対位置を推定するモデルを提案。事前観測を活用したナビゲーションタスクMem-Navで有効性を示す。
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: Mert Bulent Sariyildiz, Philippe Weinzaepfel, Guillaume Bono, Gianluca Monaci, Christian Wolf
分類: cs.RO, cs.CV
原文アブストラクト
One key aspect of spatially aware robots is the ability to "find their bearings", ie. to correctly situate themselves in previously seen spaces. In this work, we focus on this particular scenario of continuous robotics operations, where information observed before an actual episode start is exploited to optimize efficiency. We introduce a new model, Kinaema, and agent, capable of integrating a stream of visual observations while moving in a potentially large scene, and upon request, processing a query image and predicting the relative position of the shown space with respect to its current position. Our model does not explicitly store an observation history, therefore does not have hard constraints on context length. It maintains an implicit latent memory, which is updated by a transformer in a recurrent way, compressing the history of sensor readings into a compact representation. We evaluate the impact of this model in a new downstream task we call "Mem-Nav". We show that our large-capacity recurrent model maintains a useful representation of the scene, navigates to goals observed before the actual episode start, and is computationally efficient, in particular compared to classical transformers with attention over an observation history.
