Enhancing Users’ Predictions of Robotic Pouring Behaviors Using Augmented Reality: A Case Study

People effortlessly manipulate fluids due to their learned understanding of fluid dynamics, while robots struggle with complex fluid dynamic calculations, particularly in tasks like pouring. To enhance assistive robots in such tasks, we propose involving users in correcting and providing feedback by visualizing the planned pouring trajectories before they are executed. This paper investigates whether people can predict robotic pouring outcomes and make adjustments to minimize spills, using visualization devices like augmented reality. In a human-participant study, participants evaluated and adjusted robot pouring behaviors of unique configurations for various source containers. Results highlight the effectiveness of visualization tools such as augmented reality headsets, as well as traditional 2D display, especially with specific pouring parameters, and users noted their benefits in open-ended responses. This research illuminates the potential for human-robot collaboration in fluid manipulation tasks, with visualization tools reducing spills in robot-controlled pours.

I. INTRODUCTION

Individuals accumulate years of experience observing both their own and others’ actions in manipulating fluids. This learned behavior equipped us with an internal physics engine, allowing us to anticipate the outcome of a pour and identify and change necessary adjustments during the pouring process to prevent spills [1], [2]. However, it remains uncertain whether individuals can accurately predict the outcomes when a robot is manipulating fluids, particularly when they lack a precise mental model of the robot’s capabilities upon initial encounter. Users with an assistive robotic arm for pouring a drink may find themselves at risk of spills due to unfamiliarity with the robot’s behavior.