Implementation for bounded ratio reinforcement learning project

Mosaico - The data platform for Physical AI

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

FABRICS

Pytorch implementation of MeanFlow on ImageNet and CIFAR10

ROS node to publish a point cloud from a .ply file as PointCloud2.

A Modular Toolkit for Robot Kinematic Optimization

Scaling safe exploration to vision control

Tool for robust segmentation of >100 important anatomical structures in CT and MR images

Multi-modal agentic framework for surgical procedures

Shrink wrapping using the CGAL's 3D Alpha Wrapping

MONAI Generative Models makes it easy to train, evaluate, and deploy generative models and related applications

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

Model-predictive control for microcontrollers, ICRA 2024 Best Paper Award

Python implementation of MPPI (Model Predictive Path-Integral) controller to understand the basic idea. Mandatory dependencies are numpy and matplotlib only.

This project includes a variety of ultrasound image processing, such as enhancement, generation, classification, etc.

Code to implement "Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation"

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

[DEPRECATED] GLOMAP - Global Structured-from-Motion Revisited

A urdf package of kuka LBR iiwa 7 R800 for ROS

An Open-Ended Embodied Agent with Large Language Models

Python binding of SLAM graph optimization framework g2o

Summary for Introduction to machine learning at ETH Zürich (2019)

ROS service to start/stop recording a list of topics to a bag file