Enhancing Robot Learning through Learned Human-Attention Feature Maps

Daniel Scheuchenstuhl, Stefan Ulmer, Felix Resch, Luigi Berducci, Radu GrosuarXiv 2023 · DOI · arXiv

Introduction

Deep learning has significantly advanced robotic perception, yet autonomous agents often struggle with high-dimensional sensor noise. Unlike humans, who naturally filter out irrelevant visual stimuli—such as background posters or flickering lights—to focus on task-critical elements like the apex of a turn, robots frequently overfit to these distractors. This leads to poor robustness in out-of-distribution (OOD) scenarios and high data requirements for training. This paper explores a method to distill human biological attention into feature maps that guide robot learning pipelines toward task-relevant information.

Methodology

The proposed approach consists of three primary phases: data collection, attention modeling, and downstream integration.

Data Collection and Processing

Researchers utilized a miniature F1Tenth racecar operated manually by a human driver. The driver was equipped with a VPS 19 eye-tracking system to capture precise gaze points synchronized with first-person video and vehicle telemetry.

Experimental setup for collecting synchronized gaze and driving data.

To transform discrete gaze points into a usable format for neural networks, the authors converted them into continuous heatmaps. These maps use a Gaussian distribution to represent the focus area and an exponential-decay function to account for temporal persistence, ensuring the model retains information about recently viewed areas.

Model Architecture

A U-Net++ architecture was trained to predict these human-like attention heatmaps directly from raw video frames. Once trained, this model can generate "attention priors" without requiring a human in the loop. These maps were then integrated into two distinct robotic tasks:

  1. Object Detection: Modifying YOLOv7 to include the attention map as a fourth input channel (RGB + Attention).
  2. Imitation Learning: Using the maps to "mark" input frames for a ResNet18-based agent predicting steering and velocity.

Key Results and Insights

The integration of human attention served as a powerful regularizer, filtering environmental perturbations and preventing the model from overfitting to irrelevant features.

Robustness to Illumination Changes

One of the most significant findings was the increased robustness to lighting variations. In tests where brightness was perturbed from 75% to 185% of the original levels, the standard YOLOv7 model experienced performance drops between 10% and 25%. In contrast, the attention-augmented version (Att-YOLOv7) maintained nearly constant performance across all tested conditions.

Performance comparison of standard YOLOv7 vs. Attention-augmented YOLOv7 under varying illumination.

Learning Efficiency

In imitation learning tasks, the attention-aware agent demonstrated faster convergence and a lower Mean Squared Error (MSE) for driving commands. This advantage was most pronounced in data-scarce environments, suggesting that human-centric priors provide a significant "head start" by teaching the agent where to look before it begins learning how to act.

Conclusion and Future Work

By distilling human intuition into reusable feature maps, the researchers have demonstrated a path toward more robust and data-efficient robot learning. While currently focused on driving, future work will investigate the generalizability of these attention models to other domains, such as robotic manipulation and navigation in complex, multi-agent social environments.

Summary updated

Abstract

Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with which we quickly process complex visual scenes and react to changes in the environment, we think that embedding auxiliary information about focus point into robot learning would enhance efficiency and robustness of the learning process. In this paper, we propose a novel approach to model and emulate the human attention with an approximate prediction model. We then leverage this output and feed it as a structured auxiliary feature map into downstream learning tasks. We validate this idea by learning a prediction model from human-gaze recordings of manual driving in the real world. We test our approach on two learning tasks - object detection and imitation learning. Our experiments demonstrate that the inclusion of predicted human attention leads to improved robustness of the trained models to out-of-distribution samples and faster learning in low-data regime settings. Our work highlights the potential of incorporating structured auxiliary information in representation learning for robotics and opens up new avenues for research in this direction. All code and data are available online.
BibTeX
@misc{scheuchenstuhl2023enhancing,
  author = {Daniel Scheuchenstuhl and Stefan Ulmer and Felix Resch and Luigi Berducci and Radu Grosu},
  title = {{Enhancing Robot Learning through Learned Human-Attention Feature Maps}},
  year = {2023},
  eprint = {2308.15327},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.15327},
}
Figure