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

Deep learned, NVIDIA-accelerated 3D object pose estimation

NVIDIA-accelerated 3D scene reconstruction and Nav2 local costmap provider using nvblox

NVIDIA-accelerated packages for arm motion planning and control

NVIDIA Isaac Transport for ROS package for hardware-acceleration friendly movement of messages

NVIDIA-accelerated, deep learned model support for image space object detection

NVIDIA-accelerated Apriltag detection and pose estimation.

Framework for measuring sim-to-real gaps in robot joint motions. Supports different humanoids with physics simulation, real hardware data collection, and statistical analysis.

A mobile robot simulation with differential drive, depth camera, IMU and 2D LiDAR that supports ROS, ROS2, Gazebo, Ignition, and ISAAC Sim

Codebase for Kinova Gen3 training in Isaac Lab, sim2real transfer and ROS deployment.