Multi-agent Trajectory Prediction with Scalable Diffusion Transformer

Shenyu Zhang, Shixiong Kai, Chang Chen, Yuzheng Zhuang, Zhengbang Zhu, Minghuan Liu, Weinan Zhang

Keywords: multi-agent trajectory prediction, diffusion models, transformers, multi-modal distribution learning

Abstract:

Accurate prediction of multi-agent spatiotemporal systems is critical to various real-world applications, such as autonomous driving, sports, and multiplayer games.
Unfortunately, modeling multi-agent trajectories is challenging due to its complicated, interactive, and multi-modal nature.
Recently, diffusion models have achieved great success in modeling multi-modal distribution and trajectory generation, showing promising ability in resolving this problem.
Motivated by this, in this paper, we propose a novel multi-agent trajectory prediction framework, dubbed Scalable Diffusion Transformer (SDT), which is naturally designed to learn the complicated distribution and implicit interactions among agents.
We evaluate SDT on a set of real-world benchmark datasets and compare it with representative baseline methods, revealing the state-of-the-art multi-agent trajectory prediction ability of SDT in terms of accuracy and diversity.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2184