Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
Preprint
Abstract
Real-life control tasks involve matters of various substances---rigid or soft bodies, liquid, gas---each with distinct physical behaviors. This poses challenges to traditional rigid-body physics engines. Particle-based simulators have been developed to model the dynamics of these complex scenes; however, relying on approximation techniques, their simulation often deviates from real-world physics, especially in the long term. In this paper, we propose to learn a particle-based simulator for complex control tasks. Combining learning with particle-based systems brings in two major benefits: first, the learned simulator, just like other particle-based systems, acts widely on objects of different materials; second, the particle-based representation poses strong inductive bias for learning: particles of the same type have the same dynamics within. This enables the model to quickly adapt to new environments of unknown dynamics within a few observations. We demonstrate robots achieving complex manipulation tasks using the learned simulator, such as manipulating fluids and deformable foam, with experiments both in simulation and in the real world. Our study helps lay the foundation for robot learning of dynamic scenes with particle-based representations.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Propagation Networks for Model-Based Control Under Partial Observation2019
- Taking visual motion prediction to new heightfieldsComputer Vision and Image Understanding, 2019
- Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning2018
- Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning2018
- DeepMPC: Learning Deep Latent Features for Model Predictive Control2015
- Unified particle physics for real-time applicationsACM Transactions on Graphics, 2014
- Position based fluidsACM Transactions on Graphics, 2013
- MuJoCo: A physics engine for model-based control2012