Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset

Hao Zhou, Xu Yang, Mingyu Fan, Lu Qi, Xiangtai Li, Ming-Hsuan Yang, Fei Luo
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:79472-79489, 2025.

Abstract

With the growing interest in embodied and spatial intelligence, accurately predicting trajectories in 3D environments has become increasingly critical. However, no datasets have been explicitly designed to study 3D trajectory prediction. To this end, we contribute a 3D motion trajectory (3DMoTraj) dataset collected from unmanned underwater vehicles (UUVs) operating in oceanic environments. Mathematically, trajectory prediction becomes significantly more complex when transitioning from 2D to 3D. To tackle this challenge, we analyze the prediction complexity of 3D trajectories and propose a new method consisting of two key components: decoupled trajectory prediction and correlated trajectory refinement. The former decouples inter-axis correlations, thereby reducing prediction complexity and generating coarse predictions. The latter refines the coarse predictions by modeling their inter-axis correlations. Extensive experiments show that our method significantly improves 3D trajectory prediction accuracy and outperforms state-of-the-art methods. Both the 3DMoTraj dataset and the method are available at https://github.com/zhouhao94/3DMoTraj.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zhou25ag, title = {Three-Dimensional Trajectory Prediction with 3{DM}o{T}raj Dataset}, author = {Zhou, Hao and Yang, Xu and Fan, Mingyu and Qi, Lu and Li, Xiangtai and Yang, Ming-Hsuan and Luo, Fei}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {79472--79489}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zhou25ag/zhou25ag.pdf}, url = {https://proceedings.mlr.press/v267/zhou25ag.html}, abstract = {With the growing interest in embodied and spatial intelligence, accurately predicting trajectories in 3D environments has become increasingly critical. However, no datasets have been explicitly designed to study 3D trajectory prediction. To this end, we contribute a 3D motion trajectory (3DMoTraj) dataset collected from unmanned underwater vehicles (UUVs) operating in oceanic environments. Mathematically, trajectory prediction becomes significantly more complex when transitioning from 2D to 3D. To tackle this challenge, we analyze the prediction complexity of 3D trajectories and propose a new method consisting of two key components: decoupled trajectory prediction and correlated trajectory refinement. The former decouples inter-axis correlations, thereby reducing prediction complexity and generating coarse predictions. The latter refines the coarse predictions by modeling their inter-axis correlations. Extensive experiments show that our method significantly improves 3D trajectory prediction accuracy and outperforms state-of-the-art methods. Both the 3DMoTraj dataset and the method are available at https://github.com/zhouhao94/3DMoTraj.} }
Endnote
%0 Conference Paper %T Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset %A Hao Zhou %A Xu Yang %A Mingyu Fan %A Lu Qi %A Xiangtai Li %A Ming-Hsuan Yang %A Fei Luo %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zhou25ag %I PMLR %P 79472--79489 %U https://proceedings.mlr.press/v267/zhou25ag.html %V 267 %X With the growing interest in embodied and spatial intelligence, accurately predicting trajectories in 3D environments has become increasingly critical. However, no datasets have been explicitly designed to study 3D trajectory prediction. To this end, we contribute a 3D motion trajectory (3DMoTraj) dataset collected from unmanned underwater vehicles (UUVs) operating in oceanic environments. Mathematically, trajectory prediction becomes significantly more complex when transitioning from 2D to 3D. To tackle this challenge, we analyze the prediction complexity of 3D trajectories and propose a new method consisting of two key components: decoupled trajectory prediction and correlated trajectory refinement. The former decouples inter-axis correlations, thereby reducing prediction complexity and generating coarse predictions. The latter refines the coarse predictions by modeling their inter-axis correlations. Extensive experiments show that our method significantly improves 3D trajectory prediction accuracy and outperforms state-of-the-art methods. Both the 3DMoTraj dataset and the method are available at https://github.com/zhouhao94/3DMoTraj.
APA
Zhou, H., Yang, X., Fan, M., Qi, L., Li, X., Yang, M. & Luo, F.. (2025). Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:79472-79489 Available from https://proceedings.mlr.press/v267/zhou25ag.html.

Related Material