Adapting to Length Shift: FlexiLength Network for Trajectory Prediction

arXiv:2404.00742v1 Announce Type: new
Abstract: Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. However, a notable issue arises when these models are evaluated with varying observation lengths, leading to a significant performance drop, a phenomenon we term the Observation Length Shift. To address this issue, we introduce a general and …

abstract applications arxiv autonomous autonomous driving compact cs.cv datasets driving focus however issue network networks neural networks precision prediction public robotics role shift trajectory type understanding