Log In Sign Up

AGIL: Learning Attention from Human for Visuomotor Tasks

by   Ruohan Zhang, et al.

When intelligent agents learn visuomotor behaviors from human demonstrations, they may benefit from knowing where the human is allocating visual attention, which can be inferred from their gaze. A wealth of information regarding intelligent decision making is conveyed by human gaze allocation; hence, exploiting such information has the potential to improve the agents' performance. With this motivation, we propose the AGIL (Attention Guided Imitation Learning) framework. We collect high-quality human action and gaze data while playing Atari games in a carefully controlled experimental setting. Using these data, we first train a deep neural network that can predict human gaze positions and visual attention with high accuracy (the gaze network) and then train another network to predict human actions (the policy network). Incorporating the learned attention model from the gaze network into the policy network significantly improves the action prediction accuracy and task performance.


page 2

page 5

page 7

page 9

page 11

page 17


Gaze-Informed Multi-Objective Imitation Learning from Human Demonstrations

In the field of human-robot interaction, teaching learning agents from h...

Selective Eye-gaze Augmentation To Enhance Imitation Learning In Atari Games

This paper presents the selective use of eye-gaze information in learnin...

Efficiently Guiding Imitation Learning Algorithms with Human Gaze

Human gaze is known to be an intention-revealing signal in human demonst...

Utilizing Eye Gaze to Enhance the Generalization of Imitation Networks to Unseen Environments

Vision-based autonomous driving through imitation learning mimics the be...

Gaze Training by Modulated Dropout Improves Imitation Learning

Imitation learning by behavioral cloning is a prevalent method which has...

Supervising Neural Attention Models for Video Captioning by Human Gaze Data

The attention mechanisms in deep neural networks are inspired by human's...

Ensemble of LSTMs and feature selection for human action prediction

As robots are becoming more and more ubiquitous in human environments, i...