Abstract
Aerial vision-and-language navigation (VLN) enables unmanned aerial vehicles to execute long-horizon natural-language instructions from visual observations in complex three-dimensional environments. However, recent aerial VLN models often rely on large-scale vision-language backbones and dense visual histories, imposing substantial computation and memory costs that hinder onboard deployment. We propose LightVLN, a lightweight history-aware aerial VLN framework that combines a compact 0.5B language backbone with compact representations of both historical and current observations. LightVLN compresses each historical frame into a single token using visual features already computed by the policy. It further introduces history- and instruction-conditioned local aggregation to reduce the current observation from 256 to 32 visual tokens while preserving navigation-relevant spatial information. With up to 16 historical frames, the policy uses at most 48 observation-derived tokens. On the public OpenFly dataset, LightVLN achieves 50.93% Test-Seen and 36.14% Test-Unseen success rates (SR), outperforming the evaluated 7B language-backbone baselines on most reported metrics. It also achieves 25.83% SR on AerialVLN-S Val-Seen. In a reconstructed unseen campus, we deploy LightVLN on a DJI M350 RTK with an external Jetson Orin NX 16 GB for closed-loop onboard-compute real-to-sim hardware-in-the-loop (HIL) evaluation, achieving 14.61 Hz model inference and 11.13 Hz end-to-end decision updates. These results demonstrate the effectiveness and efficiency of LightVLN for aerial navigation.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zhao, Y., Li, T., He, J., Chai, R., & Zheng, X. (2026). LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation. https://omanscience.com/en/articles/lightvln-efficient-aerial-vision-and-language-navigation-with-compact-memory-and-history-guided-local-aggregation
MLA 9
Zhao, Yiming, et al. "LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation." https://omanscience.com/en/articles/lightvln-efficient-aerial-vision-and-language-navigation-with-compact-memory-and-history-guided-local-aggregation.
Chicago (author–date)
Zhao, Yiming, Tianshun Li, Jingle He, Ruonan Chai, and Xinhu Zheng. 2026. "LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation." https://omanscience.com/en/articles/lightvln-efficient-aerial-vision-and-language-navigation-with-compact-memory-and-history-guided-local-aggregation.
Harvard
Zhao, Y., Li, T., He, J., Chai, R. and Zheng, X. (2026) 'LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation', Available at: https://omanscience.com/en/articles/lightvln-efficient-aerial-vision-and-language-navigation-with-compact-memory-and-history-guided-local-aggregation.
Vancouver
Zhao Y, Li T, He J, Chai R, Zheng X. LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation. https://omanscience.com/en/articles/lightvln-efficient-aerial-vision-and-language-navigation-with-compact-memory-and-history-guided-local-aggregation
IEEE
Y. Zhao, T. Li, J. He, R. Chai, and X. Zheng, "LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation," https://omanscience.com/en/articles/lightvln-efficient-aerial-vision-and-language-navigation-with-compact-memory-and-history-guided-local-aggregation.