社交图Mamba：基于社交上下文的行人运动预测
Social Graph Mamba: Forecasting Pedestrian Movements Based on Social Context
- National Cheng Kung University（成功大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本研究提出Social Graph Mamba（SGM），用选择性状态空间模型（SSMs）结合动态交互图与社区感知模块，以线性复杂度实现行人运动预测，在基准测试和物理机器人实验中验证了其有效性。
中文摘要 AI 辅助
行人运动预测一直是拥挤环境中自主导航的基础。尽管基于注意力的方法取得了良好性能，但它们在建模社交交互时存在二次计算复杂度，限制了可扩展性。此外，现有方法通常在个体层面的预测基准上达到高准确率，但无法完全捕捉现实场景中人群的自然运动行为，尤其是群体结构。本研究提出Social Graph Mamba（SGM），一种新型架构，用在动态构建的交互图上运行的选择性状态空间模型（SSMs）取代基于注意力的社交推理。SGM引入带社交三元组分解的动态交互图，以顺序分解人群交互，以及社区感知模块，通过可微分MinCut优化有效发现群体结构，并基于群体成员资格对嵌入空间和多模态解码器进行条件设置。我们在标准基准（ETH/UCY、SDD）上的实验表明，与基于二次注意力的方法相比，SGM具有线性序列复杂度的竞争性能。我们通过将预测轨迹集成到社交力模型（SFM）中进行现实世界实现，进一步在物理机器人实验中验证了SGM。
英文摘要
Forecasting pedestrian motion has always been fundamental for autonomous navigation in crowded environments. While attention-based methods achieve strong performance, they suffer from quadratic computational complexity in modeling social interactions, limiting scalability. Additionally, the existing methods often achieve high accuracy on prediction benchmarks at the individual level, but fail to fully capture the natural movement behaviors of crowds in real-world scenarios, particularly group structures. In this study, we propose Social Graph Mamba (SGM), a novel architecture that replaces attention-based social reasoning with Selective State Space Models (SSMs) operating on dynamically constructed interaction graphs. SGM introduces a dynamic interaction graph with social triplet factorization to decompose crowd interactions sequentially, and a community-aware module to effectively discover group structures via differentiable MinCut optimization and conditions both the embedding space and multi-modal decoder on group membership. Our experiments on standard benchmarks (ETH/UCY, SDD) demonstrate competitive performance with linear sequence complexity compared to quadratic attention-based methods. We further validate SGM in physical robot experiments by integrating predicted trajectories into a Social Force Model (SFM) for real-world implementation.
