Implementation of the DLS2 framework

GPU-accelerated robotics (CUDA + C++)

This repository contains the preprint of the book "Riemannian Manifolds in Robot Learning, Optimization, and Control"

A Proprioceptive-Only Benchmark for Quadruped Robot's State Estimation

ROS2 Support for Unitree Go2

A PyTorch Implementation of Fast-SCNN: Fast Semantic Segmentation Network

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Code release for paper "You Only Segment Once: Towards Real-Time Panoptic Segmentation" [CVPR 2023]

SRU Navigation Learning - RL Training Framework

Cross-State Transition Attention Transformer for improved robotic manipulation with better temporal modeling; https://arxiv.org/abs/2510.00726

Contact estimation for quadruped robots.

An IsaacLab DirectEnv for basic quadrupedal locomotion tasks, with support for multiple quadruped robots, sim-to-sim, and sim-to-real pipelines

Panoptic-SLAM: Visual SLAM in Dynamic Environments using Panoptic Segmentation

Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

A robust visual SLAM system for dynamic environments

Parrot is an array fusion GPU library built on NVIDIA's CCCL libaries (Thrust/CUB).

Import your robot in blender and animate it!

[IROS 2025] NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU

OsmAnd

A great dynamic world generator, where you can make your own dynamic world in Gazebo and Isaac Sim

Direct IsaacLab Workflow for Legged Robots

Neural-Guided RANSAC for Estimating Epipolar Geometry from Sparse Correspondences

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

A powerful Isaac Sim extension for converting MuJoCo XML Configuration Format (MJCF) files to Universal Scene Description (USD) format

This repo contains the implementation of elevation mapping cupy for ros2 humble. The package works for x64 architecture and ARM arch for NVIDIA Jetson Orin boards

The official implementation of "Horizon Reduction Makes RL Scalable"

Model Predictive Control in JAX

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.