Can Robots Communicate Intention with a Simple Glance?

Video source: https://osf.io/7pq6m/files/42qbt

The Challenge: Reading a Robot's Intentions

Collaborative robots, or CoBots, are increasingly being deployed alongside human workers. Unlike traditional industrial robots that operate behind safety barriers, CoBots are designed to share the same workspace and cooperate directly with people.

Successful collaboration depends on predictability. When two people work together, a glance is often enough to communicate intentions and coordinate actions. We instinctively follow another person's gaze to anticipate what they will do next. But can the same mechanism work with a robot?

To investigate this question, researchers Lara Naendrup-Poell and Linda Onnasch from the Technische Universität Berlin examined how different visual cues influence human attention, performance, and trust during human-robot collaboration.

Tracking Attention in Real-Time Collaboration

Participants sat face-to-face with Sawyer, an industrial CoBot, which featured a screen displaying either abstract anthropomorphic eyes, directional arrows, or no visual cues. The participants were tasked with predicting the robot's upcoming movement target as quickly and accurately as possible.

To measure how these visual cues guided attention, the researchers used Neon eye tracking glasses. They also introduced occasional misleading cues that pointed toward the wrong target, allowing them to examine how people respond when robot communication becomes unreliable.

Figure 1: Experimental setup showing the collaborative robot, the visual cues displayed on its screen (eyes, arrows, or no cue), and the participant performing the prediction task. Adapted from Naendrup-Poell, L., & Onnasch, L. (2026). Predictive robot eyes shape visual attention, performance, and trust in interaction with an industrial CoBot. Scientific Reports, 16(1), 14171.

How People Respond to Robot Gaze: Attention, Adaptation, and Trust

The results showed that gaze-like cues can significantly improve human-robot coordination, but only when they remain reliable:

• Robot eyes guide attention most effectively: Both eyes and arrows improved prediction performance, but gaze-like eyes were the most effective at directing attention toward the robot's intended target. Participants predicted the robot's actions faster and more consistently when eye cues were present.

• People quickly adapt when cues become unreliable: As soon as misleading cues were introduced, participants changed their visual strategy. Rather than relying on the robot's display, they shifted their attention toward the moving robotic arm and began extracting information directly from its movements.

• Trust is built through reliability: Participants developed trust in the robot's cues during error-free interactions, but that trust dropped immediately when the cues became misleading. As the robot resumed accurate signaling, trust gradually recovered.

Designing More Predictable CoBots

As collaborative robots become more common in industrial settings, effective communication will play an increasingly important role in safe and efficient teamwork.

This study demonstrates that simple gaze-like cues can make robot behavior easier to anticipate and improve coordination between humans and machines. At the same time, it highlights how quickly people adapt when those signals become unreliable.

By combining wearable eye tracking with human-robot interaction research, researchers can directly observe how people interpret robot behavior in real time. These insights may help guide the design of future collaborative systems that communicate their intentions more clearly and support more intuitive human-robot teamwork.

Further Resources

• Full article: https://www.nature.com/articles/s41598-026-50476-4

• Research Center: Department of Action and Automation Psychology, Technische Universität Berlin, Berlin, Germany