Graph Neural Networks for Human-aware Social Navigation

TL;DR

This paper introduces a graph neural network approach for social navigation that models human conventions to enable robots to navigate more socially appropriately, demonstrating scalability and near-human performance.

Contribution

It proposes two graph-based models for social interaction and benchmarks them with GNNs, showing scalability and effectiveness in social navigation tasks.

Findings

Achieves close-to-human performance on SocNav1 dataset.

Demonstrates scalability with multiple social factors.

Provides open-source code for reproducibility.

Abstract

Autonomous navigation is a key skill for assistive and service robots. To be successful, robots have to navigate avoiding going through the personal spaces of the people surrounding them. Complying with social rules such as not getting in the middle of human-to-human and human-to-object interactions is also important. This paper suggests using Graph Neural Networks to model how inconvenient the presence of a robot would be in a particular scenario according to learned human conventions so that it can be used by path planning algorithms. To do so, we propose two ways of modelling social interactions using graphs and benchmark them with different Graph Neural Networks using the SocNav1 dataset. We achieve close-to-human performance in the dataset and argue that, in addition to promising results, the main advantage of the approach is its scalability in terms of the number of social factors that can be considered and easily embedded in code, in comparison with model-based approaches. The code used to train and test the resulting graph neural network is available in a public repository.