Skip to content

Aerial Gym Simulator

  • Software
  • Drones and boats
  • Simulator

A GPU-accelerated physics simulator for training aerial robots such as multirotors to fly and navigate cluttered environments with learning-based methods, built on NVIDIA Isaac Gym.

  • Closed core

Made by NTNU Autonomous Robots Lab, Norway (checked on github.com/ntnu-arl/aerial_gym_simulator/blob/HEAD/LICENSE (opens in a new tab)).

Source on GitHub: github.com/ntnu-arl/aerial_gym_simulator (opens in a new tab). Facts read at commit f0d0f05 (opens in a new tab).

Licenses

Code
BSD-3-Clause (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (BSD-3-Clause) at commit f0d0f05 (opens in a new tab), on 16 Oct 2026.

Commercial use
Unknown

It needs closed parts under their own terms: read them before any commercial use.

One part it needs is closed

  • Needs NVIDIA Isaac Gym: The README says its physics engine leverages NVIDIA Isaac Gym, a closed NVIDIA download; Isaac Lab and Isaac Sim support is "under development".

Labels

  • Closed coreIt needs closed parts: NVIDIA Isaac Gym.

What it does

  • Simulates thousands of micro aerial vehicles in parallel, including standard planar quadrotors, fully-actuated platforms and multirotors with arbitrary configurations.
  • Includes low-level and high-level geometric controllers that run on the GPU.
  • Provides customizable ray-casting LiDAR and camera sensors with depth and segmentation output.
  • Uses a custom rendering framework based on NVIDIA Warp to build custom sensors and kernel-based operations.
  • Allows fine-grained customization of environments, robots, sensors, tasks and controllers without large monolithic files.
  • Supports adding reinforcement learning control and navigation policies, with scripts to start training custom robots.

Written by Robotheca from the project's README (opens in a new tab) at commit f0d0f05.

Getting started

Difficulty
Advanced

Maintenance

Status
Maintained: a commit in the last 12 months
Newest commit
28 Jun 2026 on main
Latest release
Added Support for Unified Autonomy Stack (28 Jun 2026)

Checked on GitHub on 16 Oct 2026.

Robots on Robotheca that use it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.