VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method

Jiabin Lou, Haopeng Wang, Yuanshuai Wang, Xinyu Liu, Xuxin Lv, Yuxin Guo, Lei Huang, Rongye Shi, Wenjun Wu · N/A · 2026

Summary

Abstract Summary

Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions. However, route-level instructions commonly encode spatial priors, such as orientation, distance, and layout, that are not explicitly available from onboard sensing at deployment in open, GPS-denied environments. Benchmark performance under such interfaces therefore jointly reflects visual navigation ability and the use of route structure explicitly supplied by the task description. As a complementary formulation, we propose Vision-Only Long-Horizon Navigation (VoLN), which shifts route-relevant information from externally supplied instructions and global guidance to locally observable in-scene cues. In VoLN, goal views specify the destination, while route-relevant information is available only through locally observable in-scene cues that the agent must detect, interpret, and select online. We instantiate VoLN for aerial navigation through VoLN-UAV, a 7,210-episode benchmark that combines long-horizon goal-directed flight, continuous 3D motion, large viewpoint changes, and context-dependent beacon selection. We further provide VoLN-MLLM as an initial reference baseline. It aligns self-supervised visual features with a structured semantic space and predicts short-horizon waypoint segments from observation history, goal views, retrieved visual--semantic tokens, and proprioception. On the five-environment Test-Unseen split, it obtains success rates of 7.4%, 4.5%, and 1.8% on Easy, Normal, and Hard episodes, respectively. These results provide an initial evaluation of VoLN and reveal substantial remaining challenges in long-horizon evidence integration, cross-view goal matching, and closed-loop stability. Project page: https://admire-ljb.github.io/VoLN-UAV/

Key Points

Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions
However, route-level instructions commonly encode spatial priors, such as orientation, distance, ...
Benchmark performance under such interfaces therefore jointly reflects visual navigation ability ...
As a complementary formulation, we propose Vision-Only Long-Horizon Navigation (VoLN), which shif...
In VoLN, goal views specify the destination, while route-relevant information is available only t...

|Authors: Jiabin Lou, Haopeng Wang, Yuanshuai Wang, Xinyu Liu, Xuxin Lv, Yuxin Guo, Lei Huang, Rongye Shi, Wenjun Wu

|Venue: arXiv preprint | Year: 2026

|arXiv: 2607.21400v1

Abstract

Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions. However, route-level instructions commonly encode spatial priors, such as orientation, distance, and layout, that are not explicitly available from onboard sensing at deployment in open, GPS-denied environments. Benchmark performance under such interfaces therefore jointly reflects visual navigation ability and the use of route structure explicitly supplied by the task description. As a complementary formulation, we propose Vision-Only Long-Horizon Navigation (VoLN), which shifts route-relevant information from externally supplied instructions and global guidance to locally observable in-scene cues. In VoLN, goal views specify the destination, while route-relevant information is available only through locally observable in-scene cues that the agent must detect, interpret, and select online. We instantiate VoLN for aerial navigation through VoLN-UAV, a 7,210-episode benchmark that combines long-horizon goal-directed flight, continuous 3D motion, large viewpoint changes, and context-dependent beacon selection. We further provide VoLN-MLLM as an initial reference baseline. It aligns self-supervised visual features with a structured semantic space and predicts short-horizon waypoint segments from observation history, goal views, retrieved visual—semantic tokens, and proprioception. On the five-environment Test-Unseen split, it obtains success rates of 7.4%, 4.5%, and 1.8% on Easy, Normal, and Hard episodes, respectively. These results provide an initial evaluation of VoLN and reveal substantial remaining challenges in long-horizon evidence integration, cross-view goal matching, and closed-loop stability. Project page: https://admire-ljb.github.io/VoLN-UAV/

Key Contributions

Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions
However, route-level instructions commonly encode spatial priors, such as orientation, distance, …
Benchmark performance under such interfaces therefore jointly reflects visual navigation ability …
As a complementary formulation, we propose Vision-Only Long-Horizon Navigation (VoLN), which shif…
In VoLN, goal views specify the destination, while route-relevant information is available only t…

Topics

vision
vla
planning
benchmark

Code & Data

GitHub repository: https://github.com/Admire-ljb/VoLN-UAV

BibTeX

@article{Lou2026_260721400v1,
  title     = {VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method},
  author    = {Jiabin Lou and Haopeng Wang and Yuanshuai Wang and Xinyu Liu and Xuxin Lv and Yuxin Guo and Lei Huang and Rongye Shi and Wenjun Wu},
  year      = {2026},
  eprint    = {2607.21400v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2607.21400v1}
}