# Understanding Teacher Gaze Patterns for Robot Learning

arXiv: https://arxiv.org/abs/1907.07202 · HTML: https://mlsanity.com/paper/1907.07202/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2019.

## Built on by (most cited first, 12 of 12)

- [LazyDAgger: Reducing Context Switching in Interactive Imitation Learning](https://mlsanity.com/paper/2104.00053/) (2021)
- [Conflict Avoidance in Social Navigation -- a Survey](https://mlsanity.com/paper/2106.12113/) (2021)
- [Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback](https://mlsanity.com/paper/2310.20608/) (2023)
- [Personalized Reward Learning with Interaction-Grounded Learning (IGL)](https://mlsanity.com/paper/2211.15823/) (2022)
- [Trends, Applications, and Challenges in Human Attention Modelling](https://mlsanity.com/paper/2402.18673/) (2024)
- [Interaction-Grounded Learning with Action-inclusive Feedback](https://mlsanity.com/paper/2206.08364/) (2022)
- [Efficiently Guiding Imitation Learning Agents with Human Gaze](https://mlsanity.com/paper/2002.12500/) (2020)
- [Imitation Learning with Human Eye Gaze via Multi-Objective Prediction](https://mlsanity.com/paper/2102.13008/) (2021)
- [How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots](https://mlsanity.com/paper/2407.06459/) (2024)
- [From Interactive to Co-Constructive Task Learning](https://mlsanity.com/paper/2305.15535/) (2023)
- [Prosody as a Teaching Signal for Agent Learning: Exploratory Studies and Algorithmic Implications](https://mlsanity.com/paper/2410.23554/) (2024)
- [Object Referring-Guided Scanpath Prediction with Perception-Enhanced Vision-Language Models](https://mlsanity.com/paper/2604.20361/) (2026)

## Abstract (arXiv)

Human gaze is known to be a strong indicator of underlying human intentions and goals during manipulation tasks. This work studies gaze patterns of human teachers demonstrating tasks to robots and proposes ways in which such patterns can be used to enhance robot learning. Using both kinesthetic teaching and video demonstrations, we identify novel intention-revealing gaze behaviors during teaching. These prove to be informative in a variety of problems ranging from reference frame inference to segmentation of multi-step tasks. Based on our findings, we propose two proof-of-concept algorithms which show that gaze data can enhance subtask classification for a multi-step task up to 6% and reward inference and policy learning for a single-step task up to 67%. Our findings provide a foundation for a model of natural human gaze in robot learning from demonstration settings and present open problems for utilizing human gaze to enhance robot learning.