Robot models liquid and solid interactions for sponge manipulation
Robotic Multiphase Interaction: Manipulating Coupled Liquid and Solid Dynamics with a World Model
Robotics
Summary
This work looks at how robots can handle objects that hold liquid inside, like a wet sponge. The researchers created a simulation that shows how water moves inside a sponge as it is squeezed or lifted. Their robot model predicts how both the liquid and the sponge change together when the robot acts. This helps the robot plan actions that control water release and grip stability. Their approach improved prediction accuracy significantly compared to earlier methods.
What this means in practice
- •For robotics engineers: Generate better robot control strategies to handle deformable objects containing liquids, such as sponges or wet cloth, by predicting coupled liquid-solid changes.
- •For industrial safety teams: Reduce safety risks in manufacturing environments by modeling and predicting liquid spills caused by robotic handling of porous containers and materials.
Authors
Yixuan Feng, Peng Wang
Abstract
This work presents \textit{Robotic Multiphase Interaction (RMI)}, a setting in which liquid enters a porous material and interacts mechanically with its deforming solid skeleton. Manipulation can therefore change pore volume, expel or redistribute retained liquid, and alter grasp stability at the same time. Spilled liquid can also create safety risks in domestic and manufacturing settings. This differs from most manipulation of solid objects and from tasks that involve both liquid and solid while keeping the phases spatially separate. We study a sponge filled with water as the first RMI example. We use implicit incompressible porous flow with smoothed particle hydrodynamics as the dynamics engine and enable robotic manipulation by adding Coulomb contact memory, hybrid velocity and force regulation, and a stability gate for lifting. The resulting environment connects robot commands to changes in the coupled liquid and solid state. A world model conditioned on actions predicts how this state evolves under candidate commands, while a temporal UNet generates actions using either Diffusion Policy or rectified flow matching. Our world model reduces retained water prediction error by more than $60\%$ compared with the baseline. The best action sequence selected by the world model from policy proposals further reduces the predicted terminal water error by about half. These improvements show that modelling the coupled liquid and solid state helps the robot predict how its actions affect both the porous object and the liquid held inside.