轻量模型实现零样本连续环境视觉导航，无需额外训练
LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMs
- 用轻量级视觉语言模型处理多源输入，减少信息冗余
- 准确估计导航进度，避免文本记忆噪声干扰
- 适合资源受限场景的零样本导航应用
尽管视觉语言导航（VLN）发展迅速，但在连续环境中使用轻量级视觉语言模型（VLMs）进行零样本导航仍具挑战性，因其推理能力有限导致长时程导航不可靠。本文提出LightZeroNav，解决三大瓶颈：多源输入带来的信息冗余、由噪声文本记忆引发的进度估计不准，以及动作执行与阶段切换的任务耦合。仅使用RGB观测和轻量级开源Qwen3-VL-8B模型，LightZeroNav在无需任务特定训练、图搜索或路径点预测的情况下，性能接近GPT-4o（约200B），验证了其在零样本VLN-CE中的有效性。
原文摘要 · Abstract (English)
Although vision-language navigation (VLN) has progressed rapidly, zero-shot VLN in continuous environments (VLN-CE) remains highly challenging when using lightweight vision-language models (VLMs), whose limited reasoning capacity makes long-horizon navigation unreliable. In this paper, we propose LightZeroNav to tackle the three major bottlenecks when using lightweight VLMs in zero-shot VLN-CE,i.e.,information redundancy from multi-source inputs, inaccurate progress estimation caused by noisy textual memory, and task entanglement between action execution and stage transition. Using only RGB observations and a lightweight open-source Qwen3-VL-8B backbone, LightZeroNav achieves competitive performance with GPT-4o (~200B) without task-specific training, graph search, or waypoint predictors, demonstrating its effectiveness in zero-shot VLN-CE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。