A library for differentiable nonlinear optimization

Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

Official repo for the paper "SAGE: SLAM with Appearance and Geometry Prior for Endoscopy" (ICRA 2022)

Official code repository for ∇-Prox: Differentiable Proximal Algorithm Modeling for Large-Scale Optimization (SIGGRAPH TOG 2023)

Safe robot learning

Implementation and examples from Trajectory Optimization with Optimization-Based Dynamics https://arxiv.org/abs/2109.04928

Automatic hyperparameter tuning for DeePC. Built by Michael Cummins at the Automotaic Control Laboratory, ETH Zurich.

Preliminary code for the paper "Learning Deterministic Surrogates for Robust Convex QCQPs".

Tutorial on Deep Declarative Networks

Collection of differentiable methods for robotics applications implemented with Pytorch.