Physical Design using Differentiable Learned Simulators
- URL: http://arxiv.org/abs/2202.00728v1
- Date: Tue, 1 Feb 2022 19:56:39 GMT
- Title: Physical Design using Differentiable Learned Simulators
- Authors: Kelsey R. Allen, Tatiana Lopez-Guevara, Kimberly Stachenfeld, Alvaro
Sanchez-Gonzalez, Peter Battaglia, Jessica Hamrick, Tobias Pfaff
- Abstract summary: In inverse design, learned forward simulators are combined with gradient-based design optimization.
This framework produces high-quality designs by propagating through trajectories of hundreds of steps.
Our results suggest that despite some remaining challenges, machine learning-based simulators are maturing to the point where they can support general-purpose design optimization.
- Score: 9.380022457753938
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Designing physical artifacts that serve a purpose - such as tools and other
functional structures - is central to engineering as well as everyday human
behavior. Though automating design has tremendous promise, general-purpose
methods do not yet exist. Here we explore a simple, fast, and robust approach
to inverse design which combines learned forward simulators based on graph
neural networks with gradient-based design optimization. Our approach solves
high-dimensional problems with complex physical dynamics, including designing
surfaces and tools to manipulate fluid flows and optimizing the shape of an
airfoil to minimize drag. This framework produces high-quality designs by
propagating gradients through trajectories of hundreds of steps, even when
using models that were pre-trained for single-step predictions on data
substantially different from the design tasks. In our fluid manipulation tasks,
the resulting designs outperformed those found by sampling-based optimization
techniques. In airfoil design, they matched the quality of those obtained with
a specialized solver. Our results suggest that despite some remaining
challenges, machine learning-based simulators are maturing to the point where
they can support general-purpose design optimization across a variety of
domains.
Related papers
- Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks [93.38375271826202]
We present a method to improve generalization and robustness to distribution shifts in sim-to-real visual quadrotor navigation tasks.
We first build a simulator by integrating Gaussian splatting with quadrotor flight dynamics, and then, train robust navigation policies using Liquid neural networks.
In this way, we obtain a full-stack imitation learning protocol that combines advances in 3D Gaussian splatting radiance field rendering, programming of expert demonstration training data, and the task understanding capabilities of Liquid networks.
arXiv Detail & Related papers (2024-06-21T13:48:37Z) - Compositional Generative Inverse Design [69.22782875567547]
Inverse design, where we seek to design input variables in order to optimize an underlying objective function, is an important problem.
We show that by instead optimizing over the learned energy function captured by the diffusion model, we can avoid such adversarial examples.
In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes.
arXiv Detail & Related papers (2024-01-24T01:33:39Z) - Diffusion Generative Inverse Design [28.04683283070957]
Inverse design refers to the problem of optimizing the input of an objective function in order to enact a target outcome.
Recent developments in learned graph neural networks (GNNs) can be used for accurate, efficient, differentiable estimation of simulator dynamics.
We show how denoising diffusion diffusion models can be used to solve inverse design problems efficiently and propose a particle sampling algorithm for further improving their efficiency.
arXiv Detail & Related papers (2023-09-05T08:32:07Z) - Aligning Optimization Trajectories with Diffusion Models for Constrained
Design Generation [17.164961143132473]
We introduce a learning framework that demonstrates the efficacy of aligning the sampling trajectory of diffusion models with the optimization trajectory derived from traditional physics-based methods.
Our method allows for generating feasible and high-performance designs in as few as two steps without the need for expensive preprocessing, external surrogate models, or additional labeled data.
Our results demonstrate that TA outperforms state-of-the-art deep generative models on in-distribution configurations and halves the inference computational cost.
arXiv Detail & Related papers (2023-05-29T09:16:07Z) - DiffSkill: Skill Abstraction from Differentiable Physics for Deformable
Object Manipulations with Tools [96.38972082580294]
DiffSkill is a novel framework that uses a differentiable physics simulator for skill abstraction to solve deformable object manipulation tasks.
In particular, we first obtain short-horizon skills using individual tools from a gradient-based simulator.
We then learn a neural skill abstractor from the demonstration trajectories which takes RGBD images as input.
arXiv Detail & Related papers (2022-03-31T17:59:38Z) - Conservative Objective Models for Effective Offline Model-Based
Optimization [78.19085445065845]
Computational design problems arise in a number of settings, from synthetic biology to computer architectures.
We propose a method that learns a model of the objective function that lower bounds the actual value of the ground-truth objective on out-of-distribution inputs.
COMs are simple to implement and outperform a number of existing methods on a wide range of MBO problems.
arXiv Detail & Related papers (2021-07-14T17:55:28Z) - Designing Air Flow with Surrogate-assisted Phenotypic Niching [117.44028458220427]
We introduce surrogate-assisted phenotypic niching, a quality diversity algorithm.
It allows to discover a large, diverse set of behaviors by using computationally expensive phenotypic features.
In this work we discover the types of air flow in a 2D fluid dynamics optimization problem.
arXiv Detail & Related papers (2021-05-10T10:45:28Z) - PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable
Physics [89.81550748680245]
We introduce a new differentiable physics benchmark called PasticineLab.
In each task, the agent uses manipulators to deform the plasticine into the desired configuration.
We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
arXiv Detail & Related papers (2021-04-07T17:59:23Z) - An adaptive artificial neural network-based generative design method for
layout designs [17.377351418260577]
An adaptive artificial neural network-based generative design approach is proposed and developed.
A novel adaptive learning and optimization strategy is proposed, which allows the design space to be effectively explored.
The performance of the proposed design method is demonstrated on two heat source layout design problems.
arXiv Detail & Related papers (2021-01-29T05:32:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.