SGN-CIRL: Scene Graph-based Navigation with Curriculum, Imitation, and Reinforcement Learning

TL;DR

This paper introduces SGN-CIRL, a novel framework combining scene graph representations with curriculum, imitation, and reinforcement learning to improve robot navigation in complex, partially observable environments.

Contribution

The paper presents an original 3D scene graph-based reinforcement learning framework that integrates imitation and curriculum learning for enhanced mapless robot navigation.

Findings

Significantly increased success rate in difficult navigation scenarios

Effective use of 3D scene graphs for spatial reasoning

Open-source code available for reproducibility

Abstract

The 3D scene graph models spatial relationships between objects, enabling the agent to efficiently navigate in a partially observable environment and predict the location of the target object.This paper proposes an original framework named SGN-CIRL (3D Scene Graph-Based Reinforcement Learning Navigation) for mapless reinforcement learning-based robot navigation with learnable representation of open-vocabulary 3D scene graph. To accelerate and stabilize the training of reinforcement learning-based algorithms, the framework also employs imitation learning and curriculum learning. The first one enables the agent to learn from demonstrations, while the second one structures the training process by gradually increasing task complexity from simple to more advanced scenarios. Numerical experiments conducted in the Isaac Sim environment showed that using a 3D scene graph for reinforcement learning significantly increased the success rate in difficult navigation cases. The code is open-sourced and available at: https://github.com/Xisonik/Aloha\_graph.