Robot Burns Weeds, Will Melt Snow and Ice on Driveways
So there you are. Sitting at home. Avoiding people and places for 18 months. And several thousand dollars just burning a hole in your pocket, what do you do?
Well, you invent an AI-controlled robot with treads, that burns weeds and that has a flamethrower attached of course. What could go wrong?
Dave Niewinski invented this highly technical gardening assistant with a lot of reinforcement training of the AI and lots of pictures of his weeds
Dave Rountree wrote an article with an accompanying video about the bot on hackaday.com that will grab the interest of mechanically inclined folks. Reading the comments about the weed-burning robot and how it fits into today’s society seamlessly offers funny opinions on this project.
Once you watch the video of said robot, you will probably run to your work table and see what spare parts you have lying around. That’s kind of what Dave did.
Rountree described which parts he put together for this project. He used a Kinova Robots Gen 3 six-axis arm, mounted to an Agile-X Robotics Bunker base. Its controlled via a Connect Tech Rudi-NX box which contains an Nvidia Jetson Xavier NX Edge AI computing engine. Wow, that was a mouthful!
Connectivity from the controller to the base is via CAN bus, but, sadly no mention of how the robot arm controller is hooked up. At least this particular model sports an effector mount camera system, which can feed straight into the Jetson, simplifying the build somewhat.
To start the software side of things, [Dave] took a video using his mobile phone while walking his lawn. Next, he used RoboFlow to highlight image stills containing weeds, which were in turn used to help train a vision AI system. The actual AI training was written in Python using Google Collaboratory, which is itself based on the awesome Jupyter Notebook (see also Jupyter Lab on the main site. If you haven’t tried that yet, and if you do any data science at all, you’ll kick yourself for not doing so!) Collaboratory would not be all that useful for this by itself, except that it gives you direct, free GPU access, via the cloud, so you can use it for AI workloads without needing fancy (and currently hard to get) GPU hardware on your desk.
If you understand what Dave explained in his article then you are in a rare group indeed. If you are a layman, then take look at the article at the link below. It is cleverly written, it is technically titillating, and well, what guy wouldn’t want to have a flamethrower robot to pull out of the garage and frighten the neighbors with? It is coming on Halloween next month.
read more at hackaday.com