NereidVLA: Learning to Understand and Navigate the Underwater World

nereidvla:-learning-to-understand-and-navigate-the-underwater-world

NereidVLA: Learning to Understand and Navigate the Underwater World

[Submitted on 18 Nov 2026]

View PDF HTML (experimental)

Abstract:Underwater navigation requires translating visual spatial cues into motion, yet marine vision-language datasets rarely include paired robot trajectories. We present NereidVLA, a vision-language-action model that transfers marine spatial knowledge to language-conditioned 3D navigation. We first train Sea2Know on approximately two million marine examples to learn target grounding, spatial relations, and scene structure without paired robot-motion supervision. We then adapt it using expert trajectories executed under simulated underwater vehicle dynamics. Given RGB histories and a language instruction, NereidVLA predicts discrete motion tokens that decode into local 3D trajectories for closed-loop tracking. Evaluation combines an independent six-dimensional underwater navigation understanding benchmark with offline prediction and closed-loop navigation. Under matched navigation training and execution settings, marine spatial pretraining increases simulation success from 72.4% to 84.4%. Without fine-tuning on the real test environment, NereidVLA achieves 78.75% success in laboratory-pool robot trials, compared with 47.50% for InternVLA-N1. These results show that marine spatial supervision can support downstream motion learning and physical underwater navigation.

Submission history

From: Chenjie Zhao [view email]
[v1] Wed, 18 Nov 2026 18:19:00 UTC (16,567 KB)