AMENet: Attentive Maps Encoder Network for trajectory prediction

Hao Cheng, Wentong Liao*, Michael Ying Yang*, Bodo Rosenhahn, Monika Sester

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Trajectory prediction is critical for applications of planning safe future movements and remains challenging even for the next few seconds in urban mixed traffic. How an agent moves is affected by the various behaviors of its neighboring agents in different environments. To predict movements, we propose an end-to-end generative model named Attentive Maps Encoder Network (AMENet) that encodes the agent's motion and interaction information for accurate and realistic multi-path trajectory prediction. A conditional variational auto-encoder module is trained to learn the latent space of possible future paths based on attentive dynamic maps for interaction modeling and then is used to predict multiple plausible future trajectories conditioned on the observed past trajectories. The efficacy of AMENet is validated using two public trajectory prediction benchmarks Trajnet and InD.

Original languageEnglish
Pages (from-to)253-266
Number of pages14
JournalISPRS journal of photogrammetry and remote sensing
Volume172
Early online date14 Jan 2021
DOIs
Publication statusPublished - Feb 2021

Keywords

  • Encoder
  • Generative model
  • Trajectory prediction
  • ITC-ISI-JOURNAL-ARTICLE
  • UT-Hybrid-D

Fingerprint Dive into the research topics of 'AMENet: Attentive Maps Encoder Network for trajectory prediction'. Together they form a unique fingerprint.

Cite this