NereidVLA: Learning to Understand and Navigate the Underwater World
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.
Authors
- Dejun Li
- Mingwei Lin (ORCID: https://orcid.org/0000-0002-8583-5896)
- Xingxue Shi
- Zhiliang Zhu
- Puyue Wang
- Yuquan Xue
- Kangye Zheng
- Zhiqiang Zhao
- Chenjie Zhao
- Quan Chen
- Boyang Xu
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.48550/arxiv.2611.24864
- Primary Topic
- Underwater Vehicles and Communication Systems
- Type
- preprint