arXiv：cs.AI· Xi Chen, Zhe Liu, Xiaogang Xu, Jiafei Xu, Chunyi Zhou, Yuan Su, Rui Zeng, Tianyu Du, Kelu Yao, Chao Li, Shouling Ji·· 3 小时前
面向冻结空中VLN智能体的轨迹锚定指令翻译器 TGIT
Speaking the Navigator's Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents
AI 导读
针对冻结的 OpenFly 导航智能体，指令差距使成功率（SR）从 31.03% 降至 11.33%。研究者提出轨迹锚定指令翻译器（TGIT），在不改动导航智能体的前提下将简短意图指令翻译为可执行指令，把 Weak 输入 SR 提升至 37.93%，零样本迁移到真实人类指令时从 11.33% 升至 32.51%。
正文
Authors:Xi Chen, Zhe Liu, Xiaogang Xu, Jiafei Xu, Chunyi Zhou, Yuan Su, Rui Zeng, Tianyu Du, Kelu Yao, Chao Li, Shouling Ji
Abstract:Aerial vision-and-language navigation (VLN) agents are typically trained on detail-rich, trajectory-aligned commands, whereas users issue short, intent-driven instructions; on a frozen OpenFly navigator, this \emph{instruction gap} drops success rate (SR) from $31.03\%$ to $11.33\%$. To scale translator training, we prompt a language model with human-written style examples to convert original commands into paired, intent-centered Weak commands, which yield $15.27\%$ SR. We introduce the \textbf{Trajectory-Grounded Instruction Translator (TGIT)}, a front-end that keeps the navigator frozen and translates Weak inputs into agent-executable commands by learning from its trajectory outcomes. The resulting Weak-trained translator raises Weak-input SR to $37.93\%$ and transfers zero-shot to real human instructions ($11.33\%{\rightarrow}32.51\%$); it also improves held-out OpenFly ($4.95\%{\rightarrow}20.79\%$) and yields recovery on CityNav and AirVLN.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.10635 [cs.AI] |
| (or arXiv:2610.10635v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10635 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xi Chen [view email]
[v1]
Wed, 7 Oct 2026 13:52:37 UTC (316 KB)
来源：arXiv：cs.AI · arxiv.org