EUVIMEDEUVIMED entdecken
Crossref

Adaptive Interaction Network for Human Motion Prediction During Human–Robot Collaboration

Mengyuan Liu, Yangting Lin, Qiongjie Cui

IEEE Transactions on Image Processing · 2026 · 35 · 8484-8496

DOI: 10.1109/tip.2026.3718431 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Mengyuan Liu und 2 weiteren Autor:innen. Hauptthemen laut MEDLINE: Robotics, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Innovation in Science and Technology Foundation for The Excellent Youth Scholars.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human motion prediction during human-robot collaboration is critical for achieving safe and efficient interactions in shared environments. Unlike previous studies that have primarily focused on humans and objects, we focus on the robot-aware human motion prediction task, which explicitly models the influence of robots on human motion. This task presents new challenges, such as capturing human-robot heterogeneity and modeling complex spatial interactions. To address these issues, we develop an adaptive interaction network (AINet) model that consists of two branches: a primary branch that predicts future human motion and an auxiliary branch that estimates robot trajectories. The two branches are jointly optimized and coupled via a Local-Global Spatial Interaction (LGSI) Module, which effectively captures fine-grained and global contextual dependencies between human and robot motion sequences. Then, we introduce an Adaptive Weighted Aggregation (AWA) Module to dynamically fuse motion features using context-dependent weights, thereby increasing adaptability across diverse scenarios. Furthermore, we adopt a coarse-to-fine prediction strategy, in which a coarse pseudo-trajectory is first predicted, followed by the refinement of detailed human poses based on that trajectory. Extensive experiments on three challenging datasets reveal that our proposed method achieves superior performance, validating its effectiveness in human-robot collaboration scenarios. Our code is available at: https://github.com/LyTingHub/AINet.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsImage Processing, Computer-AssistedHumansMovementAlgorithmsPrediction Algorithms

Förderung

  • National Natural Science Foundation of China
  • Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology
  • Shenzhen Innovation in Science and Technology Foundation for The Excellent Youth Scholars

Zitieren

APA

Liu, M., Lin, Y., & Cui, Q. (2026). Adaptive Interaction Network for Human Motion Prediction During Human–Robot Collaboration. IEEE Transactions on Image Processing, 35, 8484-8496. https://doi.org/10.1109/tip.2026.3718431

Vancouver

Liu M, Lin Y, Cui Q. Adaptive Interaction Network for Human Motion Prediction During Human–Robot Collaboration. IEEE Transactions on Image Processing. 2026;35:8484-8496. doi:10.1109/tip.2026.3718431

BibTeX
@article{Liu2026,
  author = {Liu, Mengyuan and Lin, Yangting and Cui, Qiongjie},
  title = {Adaptive Interaction Network for Human Motion Prediction During Human–Robot Collaboration},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {8484--8496},
  doi = {10.1109/tip.2026.3718431}
}
Kostenlos starten →