# Perceiving and Reasoning About Liquids Using Fully Convolutional Networks

## TL;DR

This paper explores how robots can perceive and reason about liquids using fully convolutional neural networks, demonstrating the importance of temporal information for accurate detection and tracking in manipulation tasks.

## Contribution

It introduces a method employing fully convolutional networks to detect and track liquids, highlighting the significance of temporal data in robotic perception of liquids.

## Key findings

- Networks effectively perceive and track liquids in sequences.
- Temporal information improves detection accuracy.
- Datasets include realistic simulation and real robot data.

## Abstract

Liquids are an important part of many common manipulation tasks in human environments. If we wish to have robots that can accomplish these types of tasks, they must be able to interact with liquids in an intelligent manner. In this paper, we investigate ways for robots to perceive and reason about liquids. That is, a robot asks the questions What in the visual data stream is liquid? and How can I use that to infer all the potential places where liquid might be? We collected two datasets to evaluate these questions, one using a realistic liquid simulator and another on our robot. We used fully convolutional neural networks to learn to detect and track liquids across pouring sequences. Our results show that these networks are able to perceive and reason about liquids, and that integrating temporal information is important to performing such tasks well.