トップダウンとボトムアップの相互作用に基づく誘導型視覚注意モデルによるロボット姿勢予測
Guided Visual Attention Model Based on Interactions Between Top-down and Bottom-up Information for Robot Pose Prediction
Key-Query-Value形式の視覚注意モデルを提案し、クエリを外部から変更することで動的に注意対象を切り替え、ロボット姿勢予測を高精度かつデータ効率的に実現した。
著者: Hyogo Hiruma, Hiroki Mori, Hiroshi Ito, Tetsuya Ogata
分類: cs.RO
原文アブストラクト
Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the dataset collection cost cannot be ignored. Existing visual attention models tackled the problem by employing a data efficient structure which learns to extract task relevant image areas. However, since the models cannot modify attention targets after training, it is difficult to apply to dynamically changing tasks. This paper proposed a novel Key-Query-Value formulated visual attention model. This model is capable of switching attention targets by externally modifying the Query representations, namely top-down attention. The proposed model is experimented on a simulator and a real-world environment. The model was compared to existing end-to-end robot vision models in the simulator experiments, showing higher performance and data efficiency. In the real-world robot experiments, the model showed high precision along with its scalability and extendibility.
