ITPNet: Towards Instantaneous Trajectory Prediction for Autonomous Driving

Rongqing Li, Changsheng Li, Yuhang Li, Hanjie Li, Yi Chen, Dongchun Ren, Ye Yuan, Guoren Wang

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.

Keywords: Trajectory prediction

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

Abstract: Trajectory prediction of moving traffic agents is crucial for the safety of autonomous vehicles, whereas previous approaches usually rely on sufficiently long-tracked locations (e.g., 2 seconds) to predict the future locations of the agents. However, in many real-world scenarios, it is not realistic to collect adequate observations for moving agents, leading to the collapse of most prediction models. For instance, when a moving car suddenly appears and is very close to an autonomous vehicle because of the obstruction, it is quite necessary for the autonomous vehicle to quickly and accurately predict the trajectories of the car with limited tracked trajectories. In light of this, we focus on investigating the task of instantaneous trajectory prediction, i.e., two tracked locations are available during inference. To this end, we put forward a general and plug-and-play instantaneous trajectory prediction approach, called ITPNet. At its heart, we propose a backward forecasting mechanism to reversely predict the latent feature representations of unobserved historical trajectories of the agent based on its two observed locations and then leverage them as complementary information for future trajectory prediction. Moreover, due to the inevitable existence of noise and redundancy in the predicted latent feature representations and the difficulty of automatically determining the optimal length of unobserved trajectories, we further devise a Noise Redundancy Reduction Former (NRRFormer) module, which attempts to filter out noise and redundancy from a longer sequence of unobserved trajectories and integrate the filtered features and the observed features into a compact query representation for future trajectory predictions. In essence, ITPNet can be naturally compatible with existing trajectory prediction models, enabling them to gracefully handle the case of instantaneous trajectory prediction. Extensive experiments on the Argoverse and nuScenes datasets demonstrate that ITPNet outperforms the baselines by a large margin and shows its efficacy with different trajectory prediction models.

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: 3081