Visual Closed-Loop Control for Pouring Liquids

TL;DR

This paper introduces a novel approach for robots to perform precise liquid pouring using visual feedback, employing deep learning for volume estimation and demonstrating effective closed-loop control.

Contribution

It presents the first use of raw visual feedback for robotic liquid pouring, combining model-free deep learning with PID control for improved accuracy.

Findings

Model-free method outperforms model-based in volume estimation

Robot achieves an average deviation of 38ml from target

First demonstration of visual feedback for robotic pouring

Abstract

Pouring a specific amount of liquid is a challenging task. In this paper we develop methods for robots to use visual feedback to perform closed-loop control for pouring liquids. We propose both a model-based and a model-free method utilizing deep learning for estimating the volume of liquid in a container. Our results show that the model-free method is better able to estimate the volume. We combine this with a simple PID controller to pour specific amounts of liquid, and show that the robot is able to achieve an average 38ml deviation from the target amount. To our knowledge, this is the first use of raw visual feedback to pour liquids in robotics.