Physics-aware-AI / DiffCoSim
By introducing a differentiable contact model, DiffCoSim extends the applicability of Lagrangian/Hamiltonian-inspired neural networks to enable learning of hybrid dynamics.
☆31Updated last year
Related projects ⓘ
Alternatives and complementary repositories for DiffCoSim
- ☆34Updated 3 years ago
- ☆38Updated last year
- A PyTorch library for all things nonlinear control and reinforcement learning.☆44Updated 3 years ago
- DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous Control☆22Updated 4 years ago
- Official implementation for our paper "Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control"☆17Updated 2 years ago
- ☆18Updated last year
- This repository contains the source code to perform Geometry-aware Bayesian Optimization (GaBO) on Riemannian manifolds.☆49Updated 3 years ago
- Contact-Aware Symplectic Integrator Network☆11Updated last year
- Neural ODE tutorial☆9Updated 2 years ago
- Re-implementation of Hamiltonian Generative Networks paper☆33Updated 2 years ago
- Code for "Learning Control-Oriented Dynamical Structure from Data" by Spencer M. Richards, Jean-Jacques Slotine, Navid Azizan, and Marco …☆13Updated last year
- PyTorch implementation of Hamiltonian deep neural networks.☆19Updated 2 years ago
- Second-Order Neural ODE Optimizer, NeurIPS 2021 spotlight☆52Updated 3 years ago
- Koopman Kernels for Learning Dynamical Systems from Trajectory Data☆22Updated 11 months ago
- ☆27Updated 2 years ago
- Myriad is a real-world testbed that aims to bridge trajectory optimization and deep learning.☆61Updated last year
- Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.☆72Updated 2 weeks ago
- A brief JAX tutorial with examples from control theory☆12Updated 2 years ago
- Structured framework for learning mechanical systems in PyTorch☆24Updated 5 years ago
- ☆14Updated 3 years ago
- ☆15Updated last year
- Supplementary code for the paper "Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces"☆41Updated last year
- We simulate a wind tunnel, place a rectangular occlusion in it, and then use gradient descent to turn the occlusion into a wing.☆25Updated 4 years ago
- A Neural Network Approach for Real-Time High-Dimensional Optimal Control☆25Updated 2 years ago
- A differentiable simulator for robotic systems.☆30Updated 2 years ago
- [ICML 2022] Learning Efficient and Robust Ordinary Differential \\ Equations via Invertible Neural Networks☆9Updated last year
- [ICLR 2022] Path integral sampler☆43Updated last year
- Performant, differentiable reinforcement learning☆25Updated last year
- JAX implementation of the JKOnet* architecture presented in "Learning Diffusion at Lightspeed".☆14Updated last month
- Repository containing the code for Implicit Manifold Gaussian Process.☆12Updated 3 months ago