# TrajMamba: An Ego-Motion-Guided Mamba Model for Pedestrian Trajectory Prediction from an Egocentric Perspective

arXiv: https://arxiv.org/abs/2603.14739 · HTML: https://mlsanity.com/paper/2603.14739/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 25 of 25)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Diagonal State Spaces are as Effective as Structured State Spaces](https://mlsanity.com/paper/2203.14343/) (2022)
- [Leapfrog Diffusion Model for Stochastic Trajectory Prediction](https://mlsanity.com/paper/2303.10895/) (2023)
- [Point Cloud Mamba: Point Cloud Learning via State Space Model](https://mlsanity.com/paper/2403.00762/) (2024)
- [Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty](https://mlsanity.com/paper/1711.09026/) (2017)
- [Stepwise Goal-Driven Networks for Trajectory Prediction](https://mlsanity.com/paper/2103.14107/) (2021)
- [Future Person Localization in First-Person Videos](https://mlsanity.com/paper/1711.11217/) (2017)
- [TITAN: Future Forecast using Action Priors](https://mlsanity.com/paper/2003.13886/) (2020)
- [BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation](https://mlsanity.com/paper/2007.14558/) (2020)
- [Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems](https://mlsanity.com/paper/1809.07408/) (2018)
- [Bifold and Semantic Reasoning for Pedestrian Behavior Prediction](https://mlsanity.com/paper/2012.03298/) (2020)
- [VideoMamba: Spatio-Temporal Selective State Space Model](https://mlsanity.com/paper/2407.08476/) (2024)
- [PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning](https://mlsanity.com/paper/2210.07886/) (2022)
- [End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps](https://mlsanity.com/paper/2203.16910/) (2022)
- [Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision](https://mlsanity.com/paper/2012.01884/) (2020)
- [A Novel Benchmarking Paradigm and a Scale- and Motion-Aware Model for Egocentric Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2310.10424/) (2023)
- [Forecasting Pedestrian Trajectory with Machine-Annotated Training Data](https://mlsanity.com/paper/1905.03681/) (2019)
- [Indoor Future Person Localization from an Egocentric Wearable Camera](https://mlsanity.com/paper/2103.04019/) (2021)
- [On-Board Pedestrian Trajectory Prediction Using Behavioral Features](https://mlsanity.com/paper/2210.11999/) (2022)
- [Context-aware Pedestrian Trajectory Prediction with Multimodal Transformer](https://mlsanity.com/paper/2307.03786/) (2023)
- [Pedestrian Trajectory Prediction Using Dynamics-based Deep Learning](https://mlsanity.com/paper/2309.09021/) (2023)
- [Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesis](https://mlsanity.com/paper/2507.06689/) (2025)

## Abstract (arXiv)

Future trajectory prediction of a tracked pedestrian from an egocentric perspective is a key task in areas such as autonomous driving and robot navigation. The challenge of this task lies in the complex dynamic relative motion between the ego-camera and the tracked pedestrian. To address this challenge, we propose an ego-motion-guided trajectory prediction network based on the Mamba model. Firstly, two Mamba models are used as encoders to extract pedestrian motion and ego-motion features from pedestrian movement and ego-vehicle movement, respectively. Then, an ego-motion guided Mamba decoder that explicitly models the relative motion between the pedestrian and the vehicle by integrating pedestrian motion features as historical context with ego-motion features as guiding cues to capture decoded features. Finally, the future trajectory is generated from the decoded features corresponding to the future timestamps. Extensive experiments demonstrate the effectiveness of the proposed model, which achieves state-of-the-art performance on the PIE and JAAD datasets.