NoisyTraj: Robust Trajectory Prediction with Noisy Observations

Rongqing Li, Changsheng Li, Ruilin Lv, Yuhang Li, Ye Yuan, Guoren Wang

Keywords: Trajectory prediction

Abstract:

Trajectory prediction aims to forecast an agent's future trajectories based on its historical observed trajectories, which is a critical task for various applications such as autonomous driving, robotics, and surveillance systems. Most existing trajectory prediction methods assume that the observed trajectories collected for forecasting are clean. However, in real-world scenarios, noise is inevitably introduced into the observations due to errors from sensors, detection, and tracking processes, resulting in the collapse of the existing approaches. Therefore, it is essential to perform robust trajectory prediction based on noisy observations, which is a more practical scenario. In this paper, we propose NoisyTraj, a noise-agnostic approach capable of tackling the problem of trajectory prediction with arbitrary types of noisy observations. Specifically, we put forward a mutual information-based mechanism to denoise the original noisy observations. This mechanism optimizes the produced trajectories to exhibit a pattern that closely resembles the clean trajectory pattern while deviating from the noisy one.
Considering that the trajectory structure may be destroyed through the only optimization of mutual information, we introduce an additional reconstruction loss to preserve the structure information of the produced observed trajectories. Moreover, we further propose a ranking loss based on the intuitive idea that prediction performance using denoised trajectories should surpass that using the original noisy observations, thereby further enhancing performance.
Because NoisyTraj does not rely on any specific module tailored to particular noise distributions, it can handle arbitrary types of noise in principle.
Additionally, our proposed NoisyTraj can be easily integrated into existing trajectory prediction models. Extensive experiments conducted on the ETH/UCY and Stanford Drone datasets (SDD) demonstrate that NoisyTraj significantly improves the accuracy of trajectory prediction with noisy observations, compared to the baselines.

Primary Area: applications to robotics, autonomy, planning

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/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

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: 4119