Social Graph Mamba: Forecasting Pedestrian Movements Based on Social Context

Hong-Son Nguyen; Yen-Chen Liu

cs.ROAug 11, 2026

Social Graph Mamba: Forecasting Pedestrian Movements Based on Social Context

Authors: Hong-Son Nguyen, Yen-Chen Liu

Organizations: Department of Mechanical Engineering, National Cheng Kung University, Tainan 70101, Taiwan

Abstract

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.

Figures & tables

Figure 1: The overview of Social Graph Mamba framework.

Method	ETH		Hotel		Univ		Zara1		Zara2		Average
Method	ADE	FDE	ADE	FDE	ADE	FDE	ADE	FDE	ADE	FDE	ADE	FDE
Social-STGCNN [ 19 ]	0.64	1.11	0.49	0.85	0.44	0.79	0.34	0.53	0.30	0.48	0.44	0.75
SGCN [ 24 ]	0.63	1.03	0.32	0.55	0.37	0.70	0.29	0.53	0.25	0.45	0.37	0.65
STAR [ 31 ]	0.36	0.65	0.17	0.36	0.31	0.62	0.26	0.55	0.22	0.46	0.26	0.53
PECNet [ 18 ]	0.54	0.87	0.18	0.24	0.35	0.60	0.22	0.39	0.17	0.30	0.29	0.48
Trajectron++ [ 22 ]	0.43	0.86	0.12	0.19	0.22	0.43	0.17	0.32	0.12	0.25	0.21	0.41

TABLE I : Quantitative comparison on ETH/UCY benchmark (ADE/FDE in meters, minADE 20 /minFDE 20 ). Best results in bold , second best underlined . Results for comparison methods are from their original papers.

Method	minADE 20	minFDE 20
Social-STGCNN [ 19 ]	20.76	33.18
PECNet [ 18 ]	9.96	15.88
Trajectron++ [ 22 ]	19.30	32.70
AgentFormer [ 32 ]	8.05	12.45
MART [ 12 ]	7.43	11.82
Ours	5.98	10.05

TABLE II : Quantitative comparison on SDD benchmark (minADE 20 /minFDE 20 in pixels).

Figure 3: Visualization of prediction on the ETH-UCY dataset.

Configuration	minADE $\downarrow$	minFDE $\downarrow$	ADE $\downarrow$	FDE $\downarrow$
SGM (Full)	0.049	0.081	0.124	0.296
w/o Global scan	0.051	0.083	0.126	0.301
w/o Community-aware	0.051	0.085	0.129	0.310
w/o Social triplet	0.066	0.105	0.171	0.376
SGM (minimal)	0.070	0.116	0.185	0.403

TABLE III : Ablation study on the contribution of each SGM module. Evaluated on the simulated crowd dataset (ADE/FDE in meters).

$K$	minADE $\downarrow$	minFDE $\downarrow$	ADE $\downarrow$	FDE $\downarrow$
1	0.85	1.59	0.85	1.59
5	0.07	0.14	0.12	0.30
20	0.05	0.08	0.12	0.29

TABLE IV : Effect of number of trajectory modes

K

Method	Backbone	Params (M)	Inference (ms)
Social-STGCNN [ 19 ]	$O(N^{2})$	0.04	121.39
STAR [ 31 ]	$O(N^{2})$	0.96	618.37
AgentFormer [ 32 ]	$O(N^{2})$	6.50	13165.43
MART [ 12 ]	$O(N^{2})$	1.59	10.72
Ours	$O(N)$	1.55	4.27

TABLE V : Computational comparison of sequence modeling backbones for social interaction modeling with

N=50

agents.

Figure 4: Community-aware representation

Controller	Success	Time (s)	Clearance (m)	TTC
Baseline SFM	66.7	30.56	0.65 $\pm$ 0.21	0.84
SGM enhanced	83.3	38.31	0.73 $\pm$ 0.15	1.06

TABLE VI : Physical experiment results comparing baseline SFM controller (using relative positions) vs. SGM-enhanced controller (using predicted trajectories) via ten trials.

Pedestrian Trajectory Prediction

Pedestrian trajectory prediction forecasts where people will move from their observed motion and surrounding context.

See all 36 papers

Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models
May 14, 2026Po-Chien Luan, Wuyang Li, Yang Gao +1Pedestrian Behavior Modeling Pedestrian Trajectory Prediction
EPFL, Switzerland
Learn to Quantify Social Interaction with Constraints for Pedestrian Walking
Jun 16, 2026Xiaodan ShiPedestrian Behavior Modeling Pedestrian Trajectory Prediction
Department of Computer and Systems Sciences, Stockholm University
TSCA-Net: Temporal-Spatial Clique Attention for Interpretable Multimodal Pedestrian Trajectory Prediction
Jul 11, 2026Md Mustafizur Rahman, Guangchao Yang, A F M Abdun Noor +3Pedestrian Behavior Modeling Pedestrian Trajectory Prediction
College of Computer Science, Chongqing University, Chongqing, China · Department of Software Engineering, Daffodil International University, Dhaka, Bangladesh

May 14, 2026J/K move · Enter open · S save

Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models

Po-Chien Luan, Wuyang Li, Yang Gao, Alexandre Alahi

EPFL, Switzerland

Pedestrian Behavior Modeling Pedestrian Trajectory Prediction Multi-Agent Trajectory Prediction Trajectory Prediction State Space Models

Open paper AskPDF arXiv

Human trajectory forecasting is crucial for safe navigation in crowded environments, requiring models that balance accuracy with computational efficiency. Efficiently modeling social interactions is key to performance in dense crowds. Yet, most recent methods rely on attention mechanisms, which are effective at capturing complex dependencies, but incur quadratic computational costs that scale poorly with the growing number of neighbors. Recently, Selective State-Space Models have provided a linear-time alternative; however, their inherently sequential design is misaligned with the unstructured and dynamic nature of social interactions. To address this challenge, we propose Social-Mamba, a forecasting architecture that reformulates social interactions as structured sequential processes. At its core is the Cycle Mamba block, a novel module that enables continuous bidirectional information flow. Social-Mamba organizes agents on an egocentric grid and introduces social triplet factorization, which decomposes interactions into temporal, egocentric, and goal-centric scans. These are dynamically integrated through a learnable social gate and global scan to generate accurate and efficient trajectory predictions. Extensive experiments on five trajectory forecasting benchmarks show that Social-Mamba achieves state-of-the-art accuracy while offering superior parameter efficiency and computational scalability. Furthermore, embedding Social-Mamba into a flow-matching framework further enhances both accuracy and efficiency, establishing it as a flexible and robust foundation for future trajectory forecasting research. The code is publicly available: https://github.com/vita-epfl/Social-Mamba

Abstract

Pedestrian Trajectory Prediction

Explore similar work

Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models

Learn to Quantify Social Interaction with Constraints for Pedestrian Walking

TSCA-Net: Temporal-Spatial Clique Attention for Interpretable Multimodal Pedestrian Trajectory Prediction