OpenSocInt: A Multi-modal Training Environment for Human-Aware Social Navigation
By: Victor Sanchez , Chris Reinke , Ahamed Mohamed and more
Potential Business Impact:
Trains robots to understand and join human groups.
In this paper, we introduce OpenSocInt, an open-source software package providing a simulator for multi-modal social interactions and a modular architecture to train social agents. We described the software package and showcased its interest via an experimental protocol based on the task of social navigation. Our framework allows for exploring the use of different perceptual features, their encoding and fusion, as well as the use of different agents. The software is already publicly available under GPL at https://gitlab.inria.fr/robotlearn/OpenSocInt/.
Similar Papers
SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation
Robotics
Robots learn to walk politely around people.
An Efficient Open World Environment for Multi-Agent Social Learning
Machine Learning (CS)
AI learns better by watching and working with people.
HuNavSim 2.0
Robotics
Helps robots learn to walk safely around people.