Sticky-Glance: Robust Intent Recognition for Human Robot Collaboration via Single-Glance

TL;DR

This paper introduces Sticky-Glance, a gaze-based intent recognition framework for human-robot collaboration that remains accurate and robust even with minimal gaze data and dynamic environments, enhancing interaction efficiency.

Contribution

The paper presents a novel object-centric gaze grounding framework with a sticky-glance algorithm that stabilizes intent recognition under challenging conditions.

Findings

Achieves a 0.94 tracking rate for dynamic targets.

Attains a 0.98 selection accuracy for static targets.

Reduces task duration by nearly 10% in experiments.

Abstract

Gaze is a valuable means of communication for impaired people with extremely limited motor capabilities. However, robust gaze-based intent recognition in multi-object environments is challenging due to gaze noise, micro-saccades, viewpoint changes, and dynamic objects. To address this, we propose an object-centric gaze grounding framework that stabilizes intent through a sticky-glance algorithm, jointly modeling geometric distance and direction trends. The inferred intent remains anchored to the object even under short glances with minimal 3 gaze samples, achieving a tracking rate of 0.94 for dynamic targets and selection accuracy of 0.98 for static targets. We further introduce a continuous shared control and multi-modal interaction paradigm, enabling high-readiness control and human-in-loop feedback, thereby reducing task duration for nearly 10 \%. Experiments across dynamic tracking, multi-perspective alignment, a baseline comparison, user studies, and ablation studies demonstrate improved robustness, efficiency, and reduced workload compared to representative baselines.