Abstract:
Data-driven trajectory prediction is critical in autonomous vehicles, which requires high-quality data. However, discussions about the compatibility of data collected fro...Show MoreMetadata
Abstract:
Data-driven trajectory prediction is critical in autonomous vehicles, which requires high-quality data. However, discussions about the compatibility of data collected from different countries remain limited, with a typical issue being the different driving rules in various countries. Therefore, we propose a hierarchical framework for mixing left and right-hand driving data to support trajectory prediction. Integrated with a proposed LLM-based sample generation method, the framework utilizes mirroring, MMD and sample generation incrementally to reduce the domain gap between datasets. By testing the mixed results on two typical trajectory datasets, we demonstrate that this method enhances the performance of models trained on left-hand driving data when applied to right-hand driving scenarios.
Published in: IEEE Robotics and Automation Letters ( Volume: 9, Issue: 10, October 2024)