摘要
This paper addresses the challenge of fine-grained alignment in Vision-and-Language Navigation (VLN) tasks, where robots navigate realistic 3D environments based on natural language instructions. Current approaches use contrastive learning to align language with visual trajectory sequences. Nevertheless, they encounter difficulties with fine-grained vision negatives. To enhance cross-modal embeddings, we introduce a novel Bayesian Optimization-based adversarial optimization framework for creating fine-grained contrastive vision samples. To validate the proposed methodology, we conduct a series of experiments to assess the effectiveness of the enriched embeddings on fine-grained vision negatives. Experiments on the R2R offers valuable insights into the role of negative sample quality. Our source code and trained models are available at: https://github.com/HuskyKingdom/FGVLN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2027.