Underwater robot model predicts motion better and faster in water
AquaWAM: A Dynamics-aware World Action Model for Underwater Embodied Agents
RoboticsArtificial Intelligence
Summary
Underwater robots move differently than those on land because water pushes and pulls them even when they stop moving. The authors created AquaWAM, a new model that helps these robots predict their future movements by considering underwater forces like drift and currents. Instead of relying on lots of camera images, AquaWAM uses simpler sensor data to make faster and more accurate decisions. This helps underwater robots complete tasks more successfully, even when some sensors aren’t working.
What this means in practice
- •For underwater robotics engineers: Control underwater robots better by predicting their movements including passive water effects, improving task success and decision speed.
- •For marine survey teams: Use AquaWAM to enhance underwater vehicle navigation and task completion despite limited sensor data availability.
Authors
Cunhao Zhu, Yifeng Wang, Dongliang Xu, Yunzhong Hou, Yue Yao, Chi Harold Liu
Abstract
World Action Models (WAMs) are becoming increasingly important and useful for embodied intelligence, as they enable robots to anticipate the consequences of candidate actions before interacting with the physical environment. However, underwater robots are usually subject to passive dynamics, such as inertia, buoyancy, hydrodynamic drag, and persistent drift, which can continue to affect the vehicle even after an action is completed. Existing WAMs, which primarily predict action-conditioned visual observations, are not explicitly designed to capture such passive motion dynamics. In this paper, we present AquaWAM, the first World Action Model designed for underwater embodied agents. Instead of predicting future images, AquaWAM models both action-conditioned and passive physical dynamics, including the thruster dead band, the inertial glide that outlasts each command, and ambient currents. Specifically, it senses through the DVL, IMU, pressure sensor and joint encoders, while cameras supply only semantics for understanding goals and target pose. By modeling compact navigation states rather than high-dimensional visual observations, AquaWAM substantially reduces the model size and computational cost compared with conventional WAMs. Experimentally, AquaWAM achieves a 72.6% task success rate across 20 underwater tasks on the USIM benchmark, outperforming existing methods while making action decisions 2.7x faster than U0 on an NVIDIA Jetson AGX Orin. Our model also remains effective when some onboard sensor measurements are unavailable. For example, without DVL velocity measurements, our method still achieves a 61.6% success rate, compared with 39.4% for U0.