Generation of Human-aware Navigation Maps using Graph Neural Networks
This work addresses robot navigation discomfort for social acceptance, but it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of robot navigation in social situations by generating human-aware navigation maps using a Graph Neural Network and Convolutional Neural Network model, achieving results that outperform state-of-the-art methods in accuracy and navigation metrics.
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.