Deep Active Visual Attention for Real-time Robot Motion Generation: Emergence of Tool-body Assimilation and Adaptive Tool-use

no code implementations • 29 Jun 2022 • Hyogo Hiruma, Hiroshi Ito, Hiroki Mori, Tetsuya OGATA

The model incorporates a state-driven active top-down visual attention module, which acquires attentions that can actively change targets based on task states.