PanguMotion: Continuous Driving Motion Forecasting with Pangu Transformers
This work addresses motion forecasting for autonomous driving systems to improve safety, but appears incremental as it adapts existing Transformer components to a known bottleneck in temporal continuity.
The paper tackles the problem of motion forecasting in autonomous driving by addressing the limitation of existing methods that process discrete scenes independently, proposing PanguMotion which integrates Transformer blocks from a large language model to incorporate temporal continuity and historical context. The framework was evaluated on Argoverse 2 datasets reorganized into continuous sequences, though no specific performance numbers are provided in the 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.