A Toolkit to Generate Social Navigation Datasets

TL;DR

This paper introduces a toolkit for generating social navigation datasets using simulation, enabling cost-effective data collection with symbolic information for training and assessing social navigation algorithms.

Contribution

The paper presents a novel toolkit that leverages simulation to efficiently generate social navigation datasets with symbolic data, addressing limitations of real-world data collection.

Findings

Simulation-based datasets are effective for social navigation research.

The toolkit supports symbolic information like human activities and interactions.

A case study demonstrates the use of graph neural networks with the generated data.

Abstract

Social navigation datasets are necessary to assess social navigation algorithms and train machine learning algorithms. Most of the currently available datasets target pedestrians' movements as a pattern to be replicated by robots. It can be argued that one of the main reasons for this to happen is that compiling datasets where real robots are manually controlled, as they would be expected to behave when moving, is a very resource-intensive task. Another aspect that is often missing in datasets is symbolic information that could be relevant, such as human activities, relationships or interactions. Unfortunately, the available datasets targeting robots and supporting symbolic information are restricted to static scenes. This paper argues that simulation can be used to gather social navigation data in an effective and cost-efficient way and presents a toolkit for this purpose. A use case studying the application of graph neural networks to create learned control policies using supervised learning is presented as an example of how it can be used.