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 Vision-Only Long-Horizon Navigation (VoLN), a new paradigm for autonomous agents to navigate using only onboard sensors and in-scene cues, rather than relying on external instructions. They create VoLN-UAV, a benchmark for aerial navigation with 7,210 episodes that test long-horizon goal-directed flight, continuous motion, large viewpoint changes, and context-dependent beacon selection. A baseline model, VoLN-MLLM, is provided which aligns visual features with a semantic space and predicts short-horizon waypoints. The baseline achieves success rates of 7.4%, 4.5%, and 1.8% on Easy, Normal, and Hard episodes in the test split.

What the Document Says

  • The paper presents a new paradigm called Vision-Only Long-Horizon Navigation (VoLN).
  • In VoLN, agents navigate using only locally observable in-scene cues without relying on external instructions or global guidance.
  • Goal views specify the destination and route-relevant information is obtained through in-scene cues.
  • The paper introduces VoLN-UAV, a 7,210-episode benchmark for aerial navigation that tests long-horizon goal-directed flight, continuous motion, large viewpoint changes, and context-dependent beacon selection.
  • VoLN-MLLM is provided as an initial reference baseline which aligns visual features with a semantic space and predicts short-horizon waypoints using observation history, goal views, retrieved visual--semantic tokens, and proprioception.

Key Concepts Mentioned

  • Vision-Only Long-Horizon Navigation (VoLN)
  • VoLN-UAV
  • aerial navigation
  • 7,210-episode benchmark
  • VoLN-MLLM

Claims Made by the Document

  • VoLN provides a new paradigm for autonomous agents to navigate.
  • The performance of the VoLN benchmark reflects both visual navigation ability and the use of route structure from the task description.

Evidence Used

  • The paper's introduction and methods sections detail the VoLN paradigm and benchmark.

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/