水下多任务操作研究：14 个 VLA 模型在海上的模仿学习对比
Embodied at Sea: Imitation Learning for Multi-Task Underwater Manipulation
马耳他团队把 14 个 VLA 模型搬到了海底沉船上真机实测，ACT 单任务策略完胜通用 SmolVLA，结论对做具身的很有参考价值，硬件套件也开源了。
一项研究在平静和湍流水域收集了 1616 段水下操作数据，训练了 14 个不同本体感知配置的 VLA 模型（DynamicVLA）。在泳池内 1260 次真机测试中，10 个模型超过基线，最好的模型整体成功率达 93.3%。另一项案例研究在马耳他二战沉船 Coralita X127 和 Manoel Island 码头，用单任务 ACT 和通用 SmolVLA 做抓取与系泊对比，ACT 以 47.9% 的成功率远超 SmolVLA 的 7.9%。用于数据采集、训练和部署的 BLUEMBODIED KIT 已开源。
Embodied at Sea: Imitation Learning for Multi-Task Underwater Manipulation
Behavior Cloning has demonstrated promising generalization capabilities for robotic manipulation in terrestrial environments. However, marine visual distortions and dynamic currents create a severe domain shift that remains a key bottleneck in adapting generalist architectures to underwater field manipulation. To address this, 1616 episodes of underwater manipulation data were collected in calm and turbulent waters and were used to train 14 generalist Vision-Language-Action (VLA) models (DynamicVLA) with varying proprioception observation configurations. Across three tasks on 1260 gradable on-hardware rollouts in a pool, 10 models outperformed the baseline, with the highest-performing model achieving a 93.3% overall success rate, including partial successes. Results are also introduced from a case study evaluating the performance of a single-task Action Chunking Transformer (ACT) and a generalist VLA (SmolVLA) policy for two tasks in marine archaeology and conservation: grasping and mooring. Experiments are performed on an ROV on and around the WWII wreck Coralita X127 and at Manoel Island Marina, Malta. Across 748 collected episodes and 508 gradable on-hardware rollouts, the ACT policy substantially outperformed SmolVLA (47.9% vs. 7.9% pooled success rate), earning a 66.7% success rate on the most successful task at the marine archaeological site. To enable further contributions to embodied intelligence in marine field robotics, the BLUEMBODIED KIT used to collect data, train models, and deploy policies on the ROV has been open sourced.