Detection and Tracking of Liquids with Fully Convolutional Networks
This addresses the problem of enabling robots to handle liquids using robust controllers, but it is incremental as it applies existing deep learning methods to a new domain.
The paper tackled liquid perception and reasoning by applying fully-convolutional deep neural networks to detect and track liquids, finding that LSTM networks outperformed single-frame and multi-frame models in both tasks.
Recent advances in AI and robotics have claimed many incredible results with deep learning, yet no work to date has applied deep learning to the problem of liquid perception and reasoning. In this paper, we apply fully-convolutional deep neural networks to the tasks of detecting and tracking liquids. We evaluate three models: a single-frame network, multi-frame network, and a LSTM recurrent network. Our results show that the best liquid detection results are achieved when aggregating data over multiple frames, in contrast to standard image segmentation. They also show that the LSTM network outperforms the other two in both tasks. This suggests that LSTM-based neural networks have the potential to be a key component for enabling robots to handle liquids using robust, closed-loop controllers.