在源头遏制漂移：面向鲁棒视觉语言导航的回顾性校正
Nipping the Drift in the Bud: Retrospective Rectification for Robust Vision-Language Navigation
AI总结：
BudVLN通过回顾性校正和决策条件监督合成，有效缓解视觉语言导航中的分布偏移问题，提升鲁棒性与导航性能。
摘要：
视觉语言导航（VLN）要求具身智能体解读自然语言指令并在复杂的连续3D环境中导航。然而，主导的模仿学习范式受到暴露偏差的影响，即推理过程中微小的偏差会导致误差累积。尽管DaGger类方法试图通过纠正错误状态来缓解这一问题，但我们发现了一个关键限制：指令-状态不一致。迫使智能体从偏离路径的状态中学习恢复动作往往会生成与原始指令语义冲突的监督信号。为应对这些挑战，我们引入了BudVLN，一个在线框架，通过构建监督来匹配当前状态分布，从on-policy rollouts中学习。BudVLN通过反事实再锚定和决策条件监督合成进行回顾性校正，使用测地线Oracle合成起源于有效历史状态的校正轨迹，确保语义一致性。在标准R2R-CE和RxR-CE基准测试中，BudVLN一致地缓解了分布偏移，并在成功率和SPL方面实现了最先进的性能。
英文摘要：
Vision-Language Navigation (VLN) requires embodied agents to interpret natural language instructions and navigate through complex continuous 3D environments. However, the dominant imitation learning paradigm suffers from exposure bias, where minor deviations during inference lead to compounding errors. While DAgger-style approaches attempt to mitigate this by correcting error states, we identify a critical limitation: Instruction-State Misalignment. Forcing an agent to learn recovery actions from off-track states often creates supervision signals that semantically conflict with the original instruction. In response to these challenges, we introduce BudVLN, an online framework that learns from on-policy rollouts by constructing supervision to match the current state distribution. BudVLN performs retrospective rectification via counterfactual re-anchoring and decision-conditioned supervision synthesis, using a geodesic oracle to synthesize corrective trajectories that originate from valid historical states, ensuring semantic consistency. Experiments on the standard R2R-CE and RxR-CE benchmarks demonstrate that BudVLN consistently mitigates distribution shift and achieves state-of-the-art performance in both Success Rate and SPL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
