AI Insight
This paper introduces Vision-Only Long-Horizon Navigation (VoLN), a new approach where autonomous agents navigate using only visual cues from their environment rather than relying on explicit route instructions with spatial information. The researchers created VoLN-UAV, a benchmark with 7,210 episodes for aerial drone navigation, and developed VoLN-MLLM as a baseline method that achieved modest success rates of 7.4%, 4.5%, and 1.8% on easy, normal, and hard navigation tasks respectively. The approach requires agents to independently detect and interpret environmental beacons and cues to reach goal destinations shown in reference images.
Why it matters
This research addresses a critical gap in autonomous navigation for GPS-denied environments where drones or robots must operate without external guidance systems. The framework has practical applications for search and rescue operations, infrastructure inspection, and autonomous delivery systems in areas where GPS signals are unavailable or unreliable.
Understand the Science
arXiv:2607.21400v1 Announce Type: cross
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/
Source: VoLN: Vision-Only Long-Horizon Navigation—Paradigm, Benchmark, and Method