EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

iDMaTraj: Improved Diffusion Mamba Model for Stochastic Pedestrian Trajectory Prediction

Yin Wang, Feiran Fu, Ming Fang, Junlong Feng, Lijin Deng, Zhengwei Ren, Yuejianan Gu

Computers · 01.01.2026 · 15 (1) · 12

DOI: 10.3390/computers15010012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 01.01.2026. Verfasst von Yin Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhongshan Institute of Changchun University of Science and Technology, Science and Technology Development Plan Project of Jilin Provincial Department of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Trajectory prediction constitutes a key technology for intelligent systems to forecast future movements of dynamic agents, yet it faces significant challenges due to the uncertainty of motion behavior. We propose iDMa, a stochastic trajectory prediction framework that pioneers the integration of diffusion model with Mamba architecture to achieve high-precision and high-efficiency trajectory generation. Our approach introduces two key innovations: (1) a dual-parameter learning mechanism that optimizes noise estimation of mean and variance space, unlike conventional diffusion methods that employ fixed variance during the denoising process, so as to constrain the feasible domain more accurately; (2) a hybrid denoising backbone network that incorporates Transformer encoders and Mamba blocks. Compared to existing state-of-the-art methods, iDMa reduces the average displacement error (ADE) by 4.76% (0.20 vs. 0.21) on the ETH-UCY dataset and 1.85% (7.95 vs. 8.10) on the SDD dataset.

Förderung

  • Zhongshan Institute of Changchun University of Science and Technology
  • Science and Technology Development Plan Project of Jilin Provincial Department of Science and Technology

Zitieren

APA

Wang, Y., Fu, F., Fang, M., Feng, J., Deng, L., Ren, Z., & Gu, Y. (2026). iDMaTraj: Improved Diffusion Mamba Model for Stochastic Pedestrian Trajectory Prediction. Computers, 15(1), 12. https://doi.org/10.3390/computers15010012

Vancouver

Wang Y, Fu F, Fang M, Feng J, Deng L, Ren Z, et al. iDMaTraj: Improved Diffusion Mamba Model for Stochastic Pedestrian Trajectory Prediction. Computers. 2026;15(1):12. doi:10.3390/computers15010012

BibTeX
@article{Wang2026,
  author = {Wang, Yin and Fu, Feiran and Fang, Ming and Feng, Junlong and Deng, Lijin and Ren, Zhengwei and Gu, Yuejianan},
  title = {iDMaTraj: Improved Diffusion Mamba Model for Stochastic Pedestrian Trajectory Prediction},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {1},
  pages = {12},
  doi = {10.3390/computers15010012}
}
Kostenlos starten →