Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

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

Source

arXiv

arxiv.org/abs/2607.21400v1

Read the source

Source

Plain-Language Brief

Researchers introduce a new navigation challenge called Vision-Only Long-Horizon Navigation (VoLN), which aims to shift the route-relevant information from externally supplied instructions and global guidance to locally observable in-scene cues. The paper introduces VoLN-UAV, a benchmark for aerial navigation consisting of 7,210 episodes with long-horizon goal-directed flight, continuous 3D motion, large viewpoint changes, and context-dependent beacon selection. They also provide an initial baseline for this challenge called VoLN-MLLM.

What the Document Says

  • The paper introduces Vision-Only Long-Horizon Navigation (VoLN), a navigation challenge where route-relevant information is obtained from locally observable in-scene cues instead of externally supplied instructions and global guidance.
  • VoLN-UAV is a benchmark for aerial navigation consisting of 7,210 episodes with specific characteristics such as long-horizon goal-directed flight, continuous 3D motion, large viewpoint changes, and context-dependent beacon selection.
  • The paper provides an initial baseline for VoLN called VoLN-MLLM, which 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 Test-Unseen split of five environments, VoLN-MLLM obtains success rates of 7.4%, 4.5%, and 1.8% on Easy, Normal, and Hard episodes, respectively.

Key Concepts Mentioned

  • Vision-Only Long-Horizon Navigation (VoLN)
  • VoLN-UAV
  • benchmark
  • aerial navigation
  • VoLN-MLLM
  • success rates
  • Test-Unseen split

Claims Made by the Document

  • VoLN provides an initial evaluation of the new navigation challenge.
  • VoLN-MLLM is an initial baseline for VoLN.

Evidence Used

  • The paper describes the methods and results of the proposed VoLN and VoLN-MLLM.
  • The success rates obtained by VoLN-MLLM on the Test-Unseen split are provided in the paper.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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/