Ms. NAMI: Multimodal Semantic Navigation on Relative Metric Intention Graph
Shichao Zhai, Yuxiang Cui, Shuhao Ye, Xuan Yu, Sitong Mao, Shunbo Zhou, Rong Xiong, Yue Wang
Abstract
Embodied navigation in unknown environments presents the significant challenge of integrating tasks with multimodal goals into a unified framework. In this paper, we propose the Multimodal Semantic Navigation on Relative Metric Intention Graph (Ms. NAMI), a framework that integrates various navigation tasks with multimodal goals based on a relative topo-metric intention graph. A reinforcement learning based policy with a concise action space, consisting of frontier nodes and intention nodes, is designed to guide the agent to select reasonable sub-goals. A sparse reward design is introduced to reduce bias during training. Additionally, several engineering optimizations are implemented to enhance overall performance. The experimental results indicate that our method can achieve robust navigation performance in a variety of unknown environments.
BibTeX
@inproceedings{icra2025_msnamimultimodal,
title = {Ms. NAMI: Multimodal Semantic Navigation on Relative Metric Intention Graph},
author = {Shichao Zhai and Yuxiang Cui and Shuhao Ye and Xuan Yu and Sitong Mao and Shunbo Zhou and Rong Xiong and Yue Wang},
booktitle = {ICRA 2025},
year = {2025}
}