SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917299503497216 |
|---|---|
| author | Chen, Ziyi Guo, Yingnan Chu, Zedong Luo, Minghua Shen, Yanfen Sun, Mingchao Hu, Junjun Xie, Shichao Yang, Kuan Shi, Pei Gu, Zhining Liu, Lu Han, Honglin Wu, Xiaolong Xu, Mu Zhang, Yu Guo, Ning |
| author_facet | Chen, Ziyi Guo, Yingnan Chu, Zedong Luo, Minghua Shen, Yanfen Sun, Mingchao Hu, Junjun Xie, Shichao Yang, Kuan Shi, Pei Gu, Zhining Liu, Lu Han, Honglin Wu, Xiaolong Xu, Mu Zhang, Yu Guo, Ning |
| contents | Embodied navigation that adheres to social norms remains an open research challenge. Our SocialNav is a foundational model for socially-aware navigation with a hierarchical "brain-action" architecture, capable of understanding high-level social norms and generating low-level, socially compliant trajectories. To enable such dual capabilities, we construct the SocNav Dataset, a large-scale collection of 7 million samples, comprising (1) a Cognitive Activation Dataset providing social reasoning signals such as chain-of-thought explanations and social traversability prediction, and (2) an Expert Trajectories Pyramid aggregating diverse navigation demonstrations from internet videos, simulated environments, and real-world robots. A multi-stage training pipeline is proposed to gradually inject and refine navigation intelligence: we first inject general navigation skills and social norms understanding into the model via imitation learning, and then refine such skills through a deliberately designed Socially-Aware Flow Exploration GRPO (SAFE-GRPO), the first flow-based reinforcement learning framework for embodied navigation that explicitly rewards socially compliant behaviors. SocialNav achieves +38% success rate and +46% social compliance rate compared to the state-of-the-art method, demonstrating strong gains in both navigation performance and social compliance. Our project page: https://amap-eai.github.io/SocialNav/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21135 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation Chen, Ziyi Guo, Yingnan Chu, Zedong Luo, Minghua Shen, Yanfen Sun, Mingchao Hu, Junjun Xie, Shichao Yang, Kuan Shi, Pei Gu, Zhining Liu, Lu Han, Honglin Wu, Xiaolong Xu, Mu Zhang, Yu Guo, Ning Robotics Artificial Intelligence Computer Vision and Pattern Recognition Embodied navigation that adheres to social norms remains an open research challenge. Our SocialNav is a foundational model for socially-aware navigation with a hierarchical "brain-action" architecture, capable of understanding high-level social norms and generating low-level, socially compliant trajectories. To enable such dual capabilities, we construct the SocNav Dataset, a large-scale collection of 7 million samples, comprising (1) a Cognitive Activation Dataset providing social reasoning signals such as chain-of-thought explanations and social traversability prediction, and (2) an Expert Trajectories Pyramid aggregating diverse navigation demonstrations from internet videos, simulated environments, and real-world robots. A multi-stage training pipeline is proposed to gradually inject and refine navigation intelligence: we first inject general navigation skills and social norms understanding into the model via imitation learning, and then refine such skills through a deliberately designed Socially-Aware Flow Exploration GRPO (SAFE-GRPO), the first flow-based reinforcement learning framework for embodied navigation that explicitly rewards socially compliant behaviors. SocialNav achieves +38% success rate and +46% social compliance rate compared to the state-of-the-art method, demonstrating strong gains in both navigation performance and social compliance. Our project page: https://amap-eai.github.io/SocialNav/ |
| title | SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.21135 |