构建可理解社交规范的导航模型，提升机器人避人行、守礼仪能力。
SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation
- 分层架构让模型既懂社会规则又生成合规路径
- 在700万样本上训练，成功率提升38%，社交合规率提升46%
- 适合做智能机器人、自动驾驶等需要礼让行为的场景
遵循社交规范的具身导航仍是开放挑战。本文提出SocialNav，一种面向社交感知导航的基础模型，采用分层的“脑-行动”架构，能理解高层社会规范并生成低层社交合规轨迹。为支持双重能力，我们构建了SocNav数据集，包含700万条样本：(1) 认知激活数据集，提供链式思维解释与社交通行性预测等社交推理信号；(2) 专家轨迹金字塔，聚合来自互联网视频、仿真环境和真实机器人的一致导航示范。通过多阶段训练流程逐步注入并优化导航智能：先用模仿学习注入通用导航技能与社会规范理解，再通过设计精良的社交感知流探索强化学习框架（SAFE-GRPO）进行微调——这是首个显式奖励社交合规行为的基于流的强化学习框架。相比当前最优方法，SocialNav在成功率上提升38%，社交合规率提升46%，显著提升导航性能与社交一致性。项目主页：https://amap-eai.github.io/SocialNav/
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。