Human-Robot Cooperative Distribution Coupling for Hamiltonian-Constrained Social Navigation

TL;DR

This paper presents NaviDIFF, a novel Hamiltonian-constrained framework for socially-aware robot navigation that models physical interactions, manages uncertainty, and adapts to human preferences, improving safety and efficiency in human environments.

Contribution

The paper introduces NaviDIFF, integrating port-Hamiltonian dynamics, diffusion models, and reinforcement learning to enhance social navigation for robots in human-populated spaces.

Findings

Outperforms state-of-the-art in social navigation tasks

Improves stability and efficiency of robot navigation

Adapts to human preferences through reinforcement learning

Abstract

Navigating in human-filled public spaces is a critical challenge for deploying autonomous robots in real-world environments. This paper introduces NaviDIFF, a novel Hamiltonian-constrained socially-aware navigation framework designed to address the complexities of human-robot interaction and socially-aware path planning. NaviDIFF integrates a port-Hamiltonian framework to model dynamic physical interactions and a diffusion model to manage uncertainty in human-robot cooperation. The framework leverages a spatial-temporal transformer to capture social and temporal dependencies, enabling more accurate spatial-temporal environmental dynamics understanding and port-Hamiltonian physical interactive process construction. Additionally, reinforcement learning from human feedback is employed to fine-tune robot policies, ensuring adaptation to human preferences and social norms. Extensive experiments demonstrate that NaviDIFF outperforms state-of-the-art methods in social navigation tasks, offering improved stability, efficiency, and adaptability.