AirSim-NeurIPS2019-Drone-Racing
Colosseum
AirSim-NeurIPS2019-Drone-Racing | Colosseum | |
---|---|---|
1 | 2 | |
338 | 266 | |
0.0% | 5.3% | |
0.0 | 5.8 | |
over 1 year ago | 5 months ago | |
Python | C++ | |
MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
AirSim-NeurIPS2019-Drone-Racing
-
Drone Racing RL Environments
Airsim drone racing was used in a Neurips 2019 challenge, but there are some issues with the opengl/Vulkan drivers on modern GPUs. Flightmare was used in this paper, but apprently it uses simplified physics.
Colosseum
-
SWARM Simulation Platform
As someone made a comment but then removed that, we started this project using AirSim, an open source plugin for UE. However, Microsoft has shut it down so we decided to continue the open source project here: https://github.com/CodexLabsLLC/Colosseum
-
Drone Racing RL Environments
My company, Codex Labs, has taken over the AirSim project, which we rebranded as Colosseum just to avoid confusion. We are continuing this project on here: https://github.com/CodexLabsLLC/Colosseum.
What are some alternatives?
flightmare - An Open Flexible Quadrotor Simulator
symforce - Fast symbolic computation, code generation, and nonlinear optimization for robotics
gym-pybullet-drones - PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
AirSim-Drone-Racing-Lab - A framework for drone racing research, built on Microsoft AirSim.
procthor - 🏘️ Scaling Embodied AI by Procedurally Generating Interactive 3D Houses
webots - Webots Robot Simulator
Robotics-Object-Pose-Estimation - A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.
GRID-playground - Platform for General Robot Intelligence Development
apollo - An open autonomous driving platform