Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ren, Quanhao, Li, Yicheng, Song, Nan
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.16196
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911521771094016
author Ren, Quanhao
Li, Yicheng
Song, Nan
author_facet Ren, Quanhao
Li, Yicheng
Song, Nan
contents Motion forecasting is a core task in autonomous driving systems, aiming to accurately predict the future trajectories of surrounding agents to ensure driving safety. Existing methods typically process discrete driving scenes independently, neglecting the temporal continuity and historical context correlations inherent in real-world driving environments. This paper proposes PanguMotion, a motion forecasting framework for continuous driving scenarios that integrates Transformer blocks from the Pangu-1B large language model as feature enhancement modules into autonomous driving motion prediction architectures. We conduct experiments on the Argoverse 2 datasets processed by the RealMotion data reorganization strategy, transforming each independent scene into a continuous sequence to mimic real-world driving scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16196
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PanguMotion: Continuous Driving Motion Forecasting with Pangu Transformers
Ren, Quanhao
Li, Yicheng
Song, Nan
Robotics
Motion forecasting is a core task in autonomous driving systems, aiming to accurately predict the future trajectories of surrounding agents to ensure driving safety. Existing methods typically process discrete driving scenes independently, neglecting the temporal continuity and historical context correlations inherent in real-world driving environments. This paper proposes PanguMotion, a motion forecasting framework for continuous driving scenarios that integrates Transformer blocks from the Pangu-1B large language model as feature enhancement modules into autonomous driving motion prediction architectures. We conduct experiments on the Argoverse 2 datasets processed by the RealMotion data reorganization strategy, transforming each independent scene into a continuous sequence to mimic real-world driving scenarios.
title PanguMotion: Continuous Driving Motion Forecasting with Pangu Transformers
topic Robotics
url https://arxiv.org/abs/2603.16196