Guided Visual Attention Model Based on Interactions Between Top-down and Bottom-up Information for Robot Pose Prediction
This addresses the problem of adapting robot vision to dynamically changing tasks without costly dataset collection, though it appears incremental as it builds on existing visual attention models.
The paper tackles the problem of poor robot vision performance at untrained positions by proposing a novel visual attention model that can dynamically switch attention targets through external modification of Query representations. The model demonstrated higher performance and data efficiency than existing end-to-end models in simulator experiments and showed high precision, scalability, and extendibility in real-world robot experiments.
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.