mbchang/dynamics
A Compositional Object-Based Approach to Learning Physical Dynamics
The Neural Physics Engine (NPE) helps researchers and scientists studying physical dynamics predict object movement in 2D environments. You provide initial conditions of objects (like balls or objects in a walled space) and their properties, and it predicts how they will move and interact. This is ideal for computational physicists, simulation engineers, or AI researchers exploring intuitive physics models.
174 stars. No commits in the last 6 months.
Use this if you need to simulate and predict the movement of multiple interacting rigid bodies in 2D and generalize these predictions to varying object counts and scene layouts.
Not ideal if you need a high-fidelity, real-world physics simulator for complex 3D environments or systems requiring precise physical accuracy beyond simple rigid body dynamics.
Stars
174
Forks
17
Language
Lua
License
—
Category
Last pushed
Mar 07, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mbchang/dynamics"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.