Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PanguMotion: Continuous Driving Motion Forecasting with Pangu Transformers

Quanhao Ren, Yicheng Li, Nan Song

Abstract

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.

PanguMotion: Continuous Driving Motion Forecasting with Pangu Transformers

Abstract

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.
Paper Structure (30 sections, 5 equations, 1 figure, 5 tables)

This paper contains 30 sections, 5 equations, 1 figure, 5 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Motion Forecasting in Autonomous Driving
  4. Large Language Models for Visual Encoding
  5. Synergizing Continuous Forecasting with Pangu
  6. Methodology
  7. Overall Architecture
  8. Input Representation and Base Encoder
  9. Scene Interaction and Encoding
  10. Pangu Transformer Module
  11. Decoder Design
  12. Ascend NPU Adaptation
  13. Experiments
  14. Experimental Setup
  15. Datasets and Evaluation Metrics:
  16. ...and 15 more sections

Figures (1)

  • Figure 1: Overview of our PanguMotion architecture. PanguMotion adopts an encoder-decoder structure with a frozen Pangu Block designed to capture interactive relationships within each scene and across the continuous scenes.