Generation of Human-aware Navigation Maps using Graph Neural Networks

TL;DR

This paper introduces a machine learning framework combining Graph Neural Networks and CNNs to generate real-time human-aware navigation maps, improving accuracy and navigation performance in social robot navigation scenarios.

Contribution

It presents a novel GNN-CNN based model that bootstraps existing datasets to produce cost maps for social navigation, advancing the state-of-the-art in human-aware robot navigation.

Findings

Outperforms existing methods in accuracy on the dataset

Achieves better navigation metrics in simulated tasks

Demonstrates versatility for other map generation applications

Abstract

Minimising the discomfort caused by robots when navigating in social situations is crucial for them to be accepted. The paper presents a machine learning-based framework that bootstraps existing one-dimensional datasets to generate a cost map dataset and a model combining Graph Neural Network and Convolutional Neural Network layers to produce cost maps for human-aware navigation in real-time. The proposed framework is evaluated against the original one-dimensional dataset and in simulated navigation tasks. The results outperform similar state-of-the-art-methods considering the accuracy on the dataset and the navigation metrics used. The applications of the proposed framework are not limited to human-aware navigation, it could be applied to other fields where map generation is needed.