AirSim with Autoware

Ahmed Radwan
YonoHub
Published in
3 min readNov 10, 2020

--

Autoware.ai with AirSim

As illustrated in our previous articles(Autoware.ai Vision & Autoware.ai Perception), Autoware.ai blocks are made to be used on different simulators, datasets, or ROS bags. On Yonohub, you can find multiple simulators and datasets that you can directly drag and drop and use directly with Autoware.ai blocks for localization, perception, and motion planning. Super easy and amazing right?

In a previous article (Hello AirSim’s World), Ibrahim Essam presented a way to integrate AirSim in Yonohub and he made into consideration that AirSim block should be generic. So, it can be used easily by anyone who follows ROS standards.

In this article, I’m presenting to you a simple use case for AirSim and Autoware.ai integration which there is no record of someone trying it before but in Yonohub we’ve made that integration possible. So, you can use Autoware.ai blocks with AirSim without integration problems whatsoever.

Check out the following video for a quick demo:

AirSim with Autoware.ai Pipeline

The following steps show how to create and run AirSim with Autoware pipeline.

Step 1: Setup the Project Files
For this step, you’ll need to clone our repository and to do that you’ll need to open a Jupyter notebook then open a new terminal to clone the repository.

After that, you’ll need to download YoloV3 weights using the script in “airsimautoware/yolo/DownloadYOLOWeights.sh”

Step 2: Getting Autoware.AI Blocks and AirSim Block from YonoStore
Autoware.AI blocks and AirSim Block are available for free on YonoStore to purchase them. Once you bought them, it’s a drag and drop process.

Blocks to purchase:
(AirSim— ENet Segmentation — YOLO — Euclidean Clustering — Lidar PointPillars — Draw BBoxes — IMM UKF PDA Tracker — Visualize Objects— Rviz)

Step 3: Running the Pipeline
Once you purchased the blocks, you can use them directly on YonoArc to construct and run a pipeline. We made this step even easier by making the demos ready to use on our repository.

You can also follow the steps in the following tutorial:

Also, we are working on more advanced demos for AirSim with Autoware.ai. So, stay tuned for the upcoming articles.

Yonohub

Yonohub is the first cloud-based system for designing, sharing, and evaluating autonomous vehicle algorithms using just blocks. Yonohub features a drag-and-drop tool to build complex systems consisting of many blocks, a marketplace to share and monetize blocks, a builder for custom environments, and much more.

Get $25 free credits when you sign up now. For researchers and labs, contact us to learn more about Yonohub sponsorship options. Yonohub: A Cloud Collaboration Platform for Autonomous Vehicles, Robotics, and AI Development. www.yonohub.com

If you liked this article, please consider following us on Twitter at @yonohub, email us directly, or find us on LinkedIn. I’d love to hear from you if I can help you or your team with how to use YonoHub.

References

https://www.autoware.ai/
https://github.com/microsoft/AirSim

--

--