There are plenty of “robot” projects out there that are really just a small remote control platform of some sort. We often like to think of robots of having some sort of autonomy though. [Luca Fagioli] demonstrates a great example of this with his explorer robot that uses Simultaneous Localization and Mapping (SLAM) to navigate its environment.
The robot is a built on a small plastic chassis, with one gear motor per drive wheel. Running the show is an Arduino Uno R4 Wi-Fi, paired with the Sensor Shield 5.0 and an L298N motor driver board. There’s also an HC-SR04 ultrasonic sensor module onboard, mounted atop an SG-90 servo motor so it can be panned around. The ultrasonic sensor determines the range between the robot and surrounding walls, and a map is constructed at the same time as the robot is localizing itself within it. There are also infrared sensors on the bottom of the robot for detecting tape marks on the floor for checkpointing purposes.
Often, SLAM mapping is done with advanced laser rangefinders or time of flight sensors, but there are many ways to go about it as this project demonstrates. We’ve even seen it done in a distributed manner with coordinated drones combining their efforts. Overall, it’s a highly useful technique for robot navigation and wayfinding.

Claude write me a robot.
At this point you might as well buy a Roomba since you don’t know anything about “your” code anyway.
You’re absolutely correct.
I don’t know how to write code from scratch. The only thing I can do is modify someone’s or something’s existing work. As much fun as that is, your argument has convinced me to stop relying on AI’s ability of creating and interpreting code.
My esp32 projects will be put on hold until I either learn their language or have the spare funds to hire a flesh and blood programmer.
Coincidentally, I have an automated vacuum already! I took it out of the trash and rebuilt it with new parts. It’s not a Roomba however, it’s got an Android app to control it. That’ll be entertaining enough, at least until I hire a programmer.
Thank you for closing my eyes to any alternatives that aren’t flesh and blood.
I did not see a any reference to AI, what did I miss here?
Anyway, no matter how it was done, I’m pretty sure it was fun doing and it really does look cool to see it run and draw/adjust the map.
I don’t think you missed anything. There are no vibe/agent coding artifacts or claims that I could find. No Claude.md file, no “AI” commits, etc.. The first commit was adding the license file (rather than a half finished project). The github account has a bunch of other machine vision projects.
There is enough research by now to show that the right usage of AI can lead to better understanding of a topic, but if you use AI as an answer machine that takes away anything that you could learn from exploring yourself. But even in the last scenario AI is capable of generating remarkable output, so the way you use it depends on what you’re after.
That the author doesn’t know anything of the code produced is an assumption and we all know what they say about assumptions.
i think i know what they say about assumptions: that there is no “i” in “team”
That’s because the “I” is “win” you losers
Roomba is too expensive
like 30 years ago i tried to do roughly this project for an HS science course. but i didn’t have hardly any sensors or any computer really that could handle them so i got my dad to make a board that was controlled by the PC parallel port and would drive a couple DC motors and would report back if the motor was drawing excess current. so it just bumped into things, stalled the motor, and then turn-in-reverse to try to find a path around it. it had way too much mechanical noise (wheel slipping, tether-yanking) for me to even worry about all of the other sources of error / unpredictability — it was a complete failure at mapping.
anyways, that’s what i think of when i hear about slam navigation. slam reverse slam reverse
fun and games and bayesian estimation. it’s pretty impressive, because even a simple slam system is a complex beast with a lot of moving parts.