Isaac Lab

Isaac Lab is a GPU-accelerated, open-source framework from NVIDIA designed to unify and simplify robotics research workflows, including reinforcement learning (RL), imitation learning (IL), and motion planning. Built on NVIDIA Isaac Sim, it combines fast and accurate physics and sensor simulation with GPU acceleration. Isaac Lab provides a comprehensive set of tools for robot learning: over 30 ready-to-train environments, 16+ commonly available robot models (from manipulators and quadrupeds to humanoids), and integration with popular RL frameworks such as RSL RL, SKRL, RL Games, and Stable Baselines. It also supports multi-agent RL. The framework features RTX-based camera sensors (RGB, depth, segmentation), LIDAR, IMU, contact sensors, and ray casters. Its GPU acceleration enables users to run complex simulations and computations faster, which is key for iterative processes like reinforcement learning and data-intensive tasks. Isaac Lab can run locally or be distributed across the cloud. Isaac Lab is widely used for sim-to-real transfer in robotics research, supporting rigid bodies, articulated systems, and deformable object physics. The framework is open-source under the BSD-3-Clause license.