isaac-sim/IsaacLab

Health v2 · maintenance only

Adoption not part of the score

7966 stars · 3850 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Isaac Lab is a GPU-accelerated open-source framework for robot learning built on NVIDIA Isaac Sim, unifying workflows like reinforcement learning, imitation learning, and motion planning. It provides accurate physics and sensor simulation (cameras, LIDAR, contact sensors) with 16+ robot models and 30+ ready-to-train environments.

Use cases

• train reinforcement learning policies for robot manipulators
• simulate quadruped and humanoid locomotion on GPU
• run sim-to-real transfer experiments for robotics
• benchmark robot learning environments with RSL RL or SKRL
• generate sensor data like LIDAR and camera images in simulation
• scale robot training across cloud instances

When to choose

• you need GPU-parallel physics simulation for robot learning
• you want prebuilt environments and robot assets for RL research
• you are doing sim-to-real transfer with NVIDIA Isaac Sim

When to avoid

• you need lightweight simulation without NVIDIA Isaac Sim dependencies
• you only need simple 2D or non-robotics simulation
• you lack a GPU or NVIDIA hardware

Facets

framework · maturity active

simulation machine-learning reinforcement-learning robotics gpu-computing robotics reinforcement-learning simulation machine-learning gpu-computing windows python robot-learning isaac-sim sim-to-real imitation-learning motion-planning sensor-simulation humanoid-robots linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="isaac-sim/IsaacLab")