Aerial Gym -- Isaac Gym Simulator for Aerial Robots
Not on the map. Why?
Abstract (arXiv)
Developing learning-based methods for navigation of aerial robots is an intensive data-driven process that requires highly parallelized simulation. The full utilization of such simulators is hindered by the lack of parallelized high-level control methods that imitate the real-world robot interface. Responding to this need, we develop the Aerial Gym simulator that can simulate millions of multirotor vehicles parallelly with nonlinear geometric controllers for the Special Euclidean Group SE(3) for attitude, velocity and position tracking. We also develop functionalities for managing a large number of obstacles in the environment, enabling rapid randomization for learning of navigation tasks. In addition, we also provide sample environments having robots with simulated cameras capable of capturing RGB, depth, segmentation and optical flow data in obstacle-rich environments. This simulator is a step towards developing a - currently missing - highly parallelized aerial robot simulation with geometric controllers at a large scale, while also providing a customizable obstacle randomization functionality for navigation tasks. We provide training scripts with compatible reinforcement learning frameworks to navigate the robot to a goal setpoint based on attitude and velocity command interfaces. Finally, we open source the simulator and aim to develop it further to speed up rendering using alternate kernel-based frameworks in order to parallelize ray-casting for depth images thus supporting a larger number of robots.
Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 May 2023.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2023: 2; 2024: 2; 2025: 5; 2026: 2.
11 papers.
- 2023OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Controlcited by 33
- 2024Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encodingcited by 13
- 2023Task-driven Compression for Collision Encoding based on Depth Imagescited by 7
- 2025RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigationcited by 6
- 2025Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challengescited by 4
- 2025Depth Transfer: Learning to See Like a Simulator for Real-World Drone Navigationcited by 3
- 2025Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotorcited by 1
- 2025Towards Task-Oriented Flying: Framework, Infrastructure, and Principlescited by 1
- 2024Non-Prehensile Aerial Manipulation using Model-Based Deep Reinforcement Learningcited by 0
- 2026Zero-Shot UAV Navigation in Forests via Relightable 3D Gaussian Splattingcited by 0
- 2026GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebocited by 0
- 2026GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebo3 Sep 2026
- 2026Zero-Shot UAV Navigation in Forests via Relightable 3D Gaussian Splatting6 Feb 2026
- 2025Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges4 Dec 2025
- 2025Depth Transfer: Learning to See Like a Simulator for Real-World Drone Navigation18 May 2025
- 2025Towards Task-Oriented Flying: Framework, Infrastructure, and Principles21 Apr 2025
- 2025RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation4 Feb 2025
- 2025Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotor30 Jan 2025
- 2024Non-Prehensile Aerial Manipulation using Model-Based Deep Reinforcement Learning1 Jul 2024
- 2024Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding6 Feb 2024
- 2023OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control22 Sep 2023
- 2023Task-driven Compression for Collision Encoding based on Depth Images11 Sep 2023