Towards Intention Prediction for Handheld Robots: a Case of Simulated Block Copying

TL;DR

This paper presents an intention prediction model for handheld robots that uses eye gaze data to accurately forecast user actions in a block copying task, improving cooperative manipulation.

Contribution

It introduces a novel intention inference approach leveraging eye gaze profiles to predict user actions in handheld robot-assisted tasks.

Findings

Achieved 87.94% accuracy in predicting pick actions 500ms prior.

Achieved 93.25% accuracy in predicting place actions 1500ms prior.

Demonstrated effective intention prediction in a simulated block copying task.

Abstract

Within this work, we explore intention inference for user actions in the context of a handheld robot setup. Handheld robots share the shape and properties of handheld tools while being able to process task information and aid manipulation. Here, we propose an intention prediction model to enhance cooperative task solving. Within a block copy task, we collect eye gaze data using a robot-mounted remote eye tracker which is used to create a profile of visual attention for task-relevant objects in the workspace scene. These profiles are used to make predictions about user actions i.e. which block will be picked up next and where it will be placed. Our results show that our proposed model can predict user actions well in advance with an accuracy of 87.94% (500ms prior) for picking and 93.25% (1500 ms prior) for placing actions.