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

Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions.

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, 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.

The VoLN Paradigm

We formulate VoLN as a goal-directed, long-horizon embodied navigation paradigm. At execution time, the policy receives no externally supplied task-level route instructions or global navigation signals.

Instead, each episode provides a visual goal set $\mathcal{V}$ composed of images captured near the destination, while route-relevant information is available only through locally observable in-scene cues encountered through $o_{t}$ (Fig. 2 ).

The VoLN Paradigm — VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method — Figure 2: The VoLN interaction. The policy maps goal views $\mathcal{V}$, observations $o_{t}$, and proprioception $p_{t}$ to closed-loop actions $a_{t}$; $G(\mathcal{V})$ serves only for evaluation.

The VoLN-UAV Benchmark

VoLN-UAV is built with Unreal Engine and Microsoft AirSim, which provide high-fidelity rendering and UAV simulation across the benchmark environments. The environment pool contains 17 distinct environments drawn from selected scenes adapted from existing open-source aerial VLN benchmarks, including AerialVLN Liu et al. (2023) and OpenUAV Wang et al.

(2025) , together with additional custom-built environments, $\mathcal{E}=\mathcal{E}^{\mathrm{open}}\cup\mathcal{E}^{\mathrm{custom}}$.

The VoLN-UAV Benchmark — VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method — Figure 3: Representative VoLN-UAV environments.

The VoLN-MLLM Method

VoLN-UAV couples visual–semantic grounding with closed-loop trajectory generation: the agent must interpret locally observed route cues in relation to the goal views and convert this evidence into executable waypoint segments. We address these requirements with VoLN-MLLM , a two-stage visual–semantic planning framework (Fig. 5 ).

Phase I aligns DINO visual features with CLIP’s joint image–text space, allowing observations to retrieve relevant concepts from a fixed semantic bank. Phase II employs a pretrained language-model planner.

The VoLN-MLLM Method — VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method — Figure 4: Overview of VoLN-UAV. Panels (a)–(d) show trajectory collection, beacon augmentation, annotation generation, and scene-source splitting; panels (e)–(h) summarize trajectory length, beacon categories, annotation fields, and split statistics.

Experiments

All experiments follow the VoLN-UAV protocol (Sec. 4 ): at each decision step the agent receives only an egocentric RGB observation, proprioception, and the visual goal specification $\mathcal{V}$. World-frame poses are used only for supervision and evaluation and are not exposed to the policy.

Sources and Demonstrations

Figures are reproduced from Lou et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.