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

• URL: http://arxiv.org/abs/2603.14739v1
• Date: Mon, 16 Mar 2026 02:28:45 GMT
• Title: TrajMamba: An Ego-Motion-Guided Mamba Model for Pedestrian Trajectory Prediction from an Egocentric Perspective
• Abstract summary: Future trajectory prediction of a tracked pedestrian from an egocentric perspective is a key task in areas such as autonomous driving and robot navigation.<n>We propose an ego-motion-guided trajectory prediction network based on the Mamba model.<n>The proposed model achieves state-of-the-art performance on the PIE and JAAD datasets.
• Score: 3.8807073304999355
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SimWAM: A Simple World Action Model for End-to-End Autonomous Driving [66.93548079427477]
  We present SimWAM, a simple yet effective WAM that leverages future-video prediction as a training-time supervision signal.<n>An isolated attention mask keeps action prediction independent of future frames, allowing trajectory prediction without explicit future-frame generation at inference.<n>Our SimWAM achieves 91.5 PDMS on NAVSIM, surpasses state-of-the-art WAM-based planners with substantially lower latency, and transfers zero-shot to nuScenes.
  arXiv  Detail & Related papers  (2026-08-07T17:59:09Z)
• Ego-Dynamics-Augmented World Model for Autonomous Driving with Zero-Shot Cross-Chassis Adaptation [49.23697454856427]
  World model (WM)-based reinforcement learning enables sample-efficient end-to-end autonomous driving learning.<n>Most WMs operate on bird's-eye-view (BEV) representations that are inherently egocentric.<n>This work proposes DynaDreamer, a dynamics-augmented Dreamer-style reinforcement learning method.
  arXiv  Detail & Related papers  (2026-07-15T03:20:53Z)
• EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control [19.169686105053433]
  EgoPriMo is a framework for scalable and interactive humanoid motion priors.<n>It reconstructs, generates, and forecasts SMPL-based full-body motion.<n>One checkpoint improves egocentric motion generation over UniEgoMotion.
  arXiv  Detail & Related papers  (2026-06-07T07:49:19Z)
• EgoM2P: Egocentric Multimodal Multitask Pretraining [55.259234688003545]
  Building large-scale egocentric multimodal and multitask models presents unique challenges.<n> EgoM2P is a masked modeling framework that learns from temporally-aware multimodal tokens to train a large, general-purpose model for egocentric 4D understanding.<n>We will fully open-source EgoM2P to support the community and advance egocentric vision research.
  arXiv  Detail & Related papers  (2025-06-09T15:59:25Z)
• MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos [27.766405152248055]
  Hand trajectory prediction plays a vital role in comprehending human motion patterns. However, capturing high-level human intentions consistent with reasonable temporal causality is challenging when only egocentric videos are available. We propose a novel hand trajectory prediction method dubbed MADiff, which forecasts future hand waypoints with diffusion models.
  arXiv  Detail & Related papers  (2024-09-04T12:06:33Z)
• MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model [18.607106274732885]
  We introduce a Mamba-based motion model named Mamba moTion Predictor (MTP) MTP takes the spatial-temporal location dynamics of objects as input, captures the motion pattern using a bi-Mamba encoding layer, and predicts the next motion. Our proposed tracker, MambaTrack, demonstrates advanced performance on benchmarks such as Dancetrack and SportsMOT.
  arXiv  Detail & Related papers  (2024-08-17T11:58:47Z)
• LG-Traj: LLM Guided Pedestrian Trajectory Prediction [9.385936248154987]
  We introduce LG-Traj, a novel approach to generate motion cues present in pedestrian past/observed trajectories. These motion cues, along with pedestrian coordinates, facilitate a better understanding of the underlying representation. Our method employs a transformer-based architecture comprising a motion encoder to model motion patterns and a social decoder to capture social interactions among pedestrians.
  arXiv  Detail & Related papers  (2024-03-12T19:06:23Z)
• Humanoid Locomotion as Next Token Prediction [84.21335675130021]
  Our model is a causal transformer trained via autoregressive prediction of sensorimotor trajectories. We show that our model enables a full-sized humanoid to walk in San Francisco zero-shot. Our model can transfer to the real world even when trained on only 27 hours of walking data, and can generalize commands not seen during training like walking backward.
  arXiv  Detail & Related papers  (2024-02-29T18:57:37Z)
• Social-Transmotion: Promptable Human Trajectory Prediction [65.80068316170613]
  Social-Transmotion is a generic Transformer-based model that exploits diverse and numerous visual cues to predict human behavior.<n>Our approach is validated on multiple datasets, including JTA, JRDB, Pedestrians and Cyclists in Road Traffic, and ETH-UCY.
  arXiv  Detail & Related papers  (2023-12-26T18:56:49Z)
• MotionTrack: Learning Motion Predictor for Multiple Object Tracking [68.68339102749358]
  We introduce a novel motion-based tracker, MotionTrack, centered around a learnable motion predictor. Our experimental results demonstrate that MotionTrack yields state-of-the-art performance on datasets such as Dancetrack and SportsMOT.
  arXiv  Detail & Related papers  (2023-06-05T04:24:11Z)
• InCrowdFormer: On-Ground Pedestrian World Model From Egocentric Views [28.54213112712818]
  We introduce an on-ground Pedestrian World Model that can predict how pedestrians move around an observer in the crowd on the ground plane. InCrowdFormer fully leverages the Transformer architecture by modeling pedestrian interaction and egocentric to top-down view transformation with attention. We encode the uncertainties arising from unknown pedestrian heights with latent codes to predict the posterior distributions of pedestrian positions.
  arXiv  Detail & Related papers  (2023-03-16T17:51:02Z)
• PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning [10.812772606528172]
  We propose a novel framework that relies on different data modalities to predict future trajectories and crossing actions of pedestrians from an ego-centric perspective. We show that our model improves state-of-the-art in trajectory and action prediction by up to 22% and 13% respectively on various metrics.
  arXiv  Detail & Related papers  (2022-10-14T15:12:00Z)
• Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion [87.77727495366702]
  We introduce the new task of pedestrian stop and go forecasting. Considering the lack of suitable existing datasets for it, we release TRANS, a benchmark for explicitly studying the stop and go behaviors of pedestrians in urban traffic. We build it from several existing datasets annotated with pedestrians' walking motions, in order to have various scenarios and behaviors.
  arXiv  Detail & Related papers  (2022-03-04T18:39:31Z)
• History Repeats Itself: Human Motion Prediction via Motion Attention [81.94175022575966]
  We introduce an attention-based feed-forward network that explicitly leverages the observation that human motion tends to repeat itself. In particular, we propose to extract motion attention to capture the similarity between the current motion context and the historical motion sub-sequences. Our experiments on Human3.6M, AMASS and 3DPW evidence the benefits of our approach for both periodical and non-periodical actions.
  arXiv  Detail & Related papers  (2020-07-23T02:12:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.