Fluid directed rigid body control using deep reinforcement learning

By Pingchuan Ma, Yunsheng Tian, Zherong Pan, Bo Ren, Dinesh Manocha. 2018

77 citations recorded by the source corpus.

We present a learning-based method to control a coupled 2D system involving both fluid and rigid bodies. Our approach is used to modify the fluid/rigid simulator's behavior by applying control forces only at the simulation domain boundaries. The rest of the domain, corresponding to the interior, is governed by the Navier-Stokes equation for fluids and Newton-Euler's equation for the rigid bodies. We represent our controller using a general neural-net, which is trained using deep reinforcement learning. Our formulation decomposes a control task into two stages: a precomputation training stage and an online generation stage. We utilize various fluid properties, e.g., the liquid's velocity field or the smoke's density field, to enhance the controller's performance. We set up our evaluation benchmark by letting controller drive fluid jets move on the domain boundary and allowing them to shoot fluids towards a rigid body to accomplish a set of challenging 2D tasks such as keeping a rigid body balanced, playing a two-player ping-pong game, and driving a rigid body to sequentially hit specified points on the wall. In practice, our approach can generate physically plausible animations.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

Bin Dong

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle (2019, background): “1 Introduction Deep neural networks achieve state-of-the-art performance on many tasks [4,8,16,21,25,44].”
A review on Deep Reinforcement Learning for Fluid Mechanics (2019, methodology): “To that end, an autoencoder was trained simultaneously to the agent to reduce the state dimensionality (with a dimension reduction from around 8000 to 70), in a similar fashion to Ma et al. (2018) (see ﬁgure 10).”