mlsanityData to 7 Oct 2026

PanguMotion: Continuous Driving Motion Forecasting with Pangu Transformers

arXiv 2603.16196 ↗First posted 17 Mar 2026cs.ROcited by 0

On the map: End-to-end autonomous driving → Generative simulation for driving

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generative simulation for driving, one of 9 directions in End-to-end autonomous driving. Builds on 24 of its 27 references that are in the map. First posted on arXiv 17 Mar 2026.

Builds on

24 of 27 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2020Scaling Laws for Neural Language Modelscited by 6,411
  4. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  5. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  6. 2019MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictioncited by 417
  7. 2020Learning Lane Graph Representations for Motion Forecastingcited by 380
  8. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  9. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
  10. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 279
  11. 2019CoverNet: Multimodal Behavior Prediction using Trajectory Setscited by 259
  12. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
12 more
  1. 2022Neighborhood Attention Transformercited by 235
  2. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  3. 2023Grounding Language Models to Images for Multimodal Inputs and Outputscited by 129
  4. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  5. 2021LaneRCNN: Distributed Representations for Graph-Centric Motion Forecastingcited by 112
  6. 2021Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversalscited by 112
  7. 2022HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encodingcited by 109
  8. 2023Language Models Implement Simple Word2Vec-style Vector Arithmeticcited by 97
  9. 2025Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognitioncited by 61
  10. 2023Frozen Transformers in Language Models Are Effective Visual Encoder Layerscited by 39
  11. 2023FIND: A Function Description Benchmark for Evaluating Interpretability Methodscited by 32
  12. 2024Motion Forecasting in Continuous Drivingcited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Efficient Baselines for Motion Prediction in Autonomous Driving
  2. 2024Large Language Models Powered Context-aware Motion Prediction in Autonomous Driving
  3. 2025Enhanced Motion Forecasting with Plug-and-Play Multimodal Large Language Models
  4. 2025Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives
  5. 2026SparseWorld: Enhancing End-to-End Autonomous Driving via World Models with Sparse Scene Representation
  6. 2024DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT
  7. 2025Future-Aware Interaction Network For Motion Forecasting
  8. 2021Scene Transformer: A unified architecture for predicting multiple agent trajectories