面向视觉语言导航的递归视觉想象与自适应语言接地
Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation
AI总结：
针对视觉语言导航中场景表示过细、视觉-语言对齐模糊的问题，提出结合递归视觉想象与自适应语言接地的导航策略，在VLN-CE和ObjectNav任务上性能超越现有最优方法。
摘要：
视觉语言导航（Vision Language Navigation, VLN）通常要求智能体在未知场景中遵循语言指令，导航至指定物体或远端区域。这类任务需要整合历史视觉观测以实现语言接地，这对长序列导航决策至关重要。然而，现有智能体存在场景表示过于细碎、视觉-语言对齐模糊的问题，削弱了其对利于导航的高层场景先验的理解，易引发违反语言指令的行为。针对这些问题，我们提出一种导航策略，通过递归总结沿途视觉感知，并将其与指令自适应对齐以增强语言接地。具体而言，通过将历史轨迹结构化建模为紧凑神经网格，我们提出了多种递归视觉想象（Recursive Visual Imagination, RVI）技术，促使智能体关注视觉转换规律与场景语义布局，而非处理具有误导性的几何细节。随后，我们提出自适应语言接地（Adaptive Linguistic Grounding, ALG）技术，将习得的情境记忆与不同语言成分有针对性地对齐。这种细粒度语义匹配有助于准确预判导航动作与进度。我们的导航策略在具有挑战性的VLN-CE和ObjectNav任务上优于现有最优方法，证明了RVI和ALG技术在VLN任务中的优越性。
英文摘要：
Vision Language Navigation (VLN) typically requires agents to navigate to specified objects or remote regions in unknown scenes by obeying linguistic commands. Such tasks require organizing historical visual observations for linguistic grounding, which is critical for long-sequence navigational decisions. However, current agents suffer from overly detailed scene representation and ambiguous vision-language alignment, which weaken their comprehension of navigation-friendly high-level scene priors and easily lead to behaviors that violate linguistic commands. To tackle these issues, we propose a navigation policy by recursively summarizing along-the-way visual perceptions, which are adaptively aligned with commands to enhance linguistic grounding. In particular, by structurally modeling historical trajectories as compact neural grids, several Recursive Visual Imagination (RVI) techniques are proposed to motivate agents to focus on the regularity of visual transitions and semantic scene layouts, instead of dealing with misleading geometric details. Then, an Adaptive Linguistic Grounding (ALG) technique is proposed to align the learned situational memories with different linguistic components purposefully. Such fine-grained semantic matching facilitates the accurate anticipation of navigation actions and progress. Our navigation policy outperforms the state-of-the-art methods on the challenging VLN-CE and ObjectNav tasks, showing the superiority of our RVI and ALG techniques for VLN.
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。
