cs.CVNov 18, 2026

NereidVLA: Learning to Understand and Navigate the Underwater World

Authors: Chenjie Zhao, Zhiliang Zhu, Quan Chen, Yuquan Xue, Xingxue Shi, Puyue Wang, Zhiqiang Zhao, Kangye Zheng, 

Organizations: Zhejiang University · Harbin Engineering University · Nanyang Technological University · Harbin Institute of Technology · 

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.

Figures & tables

Explore similar work

CardsList
  1. FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation

    Jun 29, 2026Lingfeng Zhang, Zeying Gong, Xiaoshuai Hao +7World ModelsVision-Language Navigation

  2. USI-Brain: Enhancing Underwater Spatial Intelligence via Spatial Data-Driven Vision-Language Modeling

    Nov 4, 2026Zhiliang Zhu, Zhiqiang Zhao, Xie'an Jiang +3Multimodal Spatial ReasoningSpatial Reasoning

  3. SpaAct: Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation

    Apr 30, 2026Pengna Li, Kangyi Wu, Shaoqing Xu +7VLM AdaptationVision-Language Navigation