Additional Resources#
External tutorials, research projects, and tools for robot learning and deployment.
Sim-to-Real Resources#
Examples of training policies in simulation and deploying them on robots:
Closing the Sim-to-Real Gap: Training Spot Quadruped Locomotion with NVIDIA Isaac Lab is a detailed guide for training a quadruped locomotion policy for the Spot Quadruped from Boston Dynamics, and deploying it to the real robot.
LLM Generated Reward Functions#
Eureka uses an LLM to generate and tune reinforcement-learning reward functions.
Isaac Lab Eureka provides the reward-generation pipeline for direct Isaac Lab environments.
Eureka! NVIDIA Research Breakthrough Puts New Spin on Robot Learning is a blog post that covers the broad idea of this reward generation process.
Simulation Features#
The following resources cover Isaac Sim workflows. For Isaac Lab’s physics and rendering options, see Physics Backends and Renderers.
Simulation Performance Guide is a best practice guide for obtaining the best simulation performance from OmniPhysics.
Deploying Policies in Isaac Sim is an Isaac Sim tutorial on how to use trained policies within the simulation.
Supercharge Robotics Workflows with AI and Simulation Using NVIDIA Isaac Sim 4.0 and NVIDIA Isaac Lab describes the features introduced in Isaac Sim 4.0.
Fast-Track Robot Learning in Simulation Using NVIDIA Isaac Lab introduces Isaac Lab’s robot-learning workflows.