Playing Rock, Paper Scissors With A Time Of Flight Sensor

You can do all kinds of wonderful things with cameras and image recognition. However, sometimes spatial data is useful, too. As [madmcu] demonstrates, you can use depth data from a time-of-flight sensor for gesture recognition, as seen in this rock-paper-scissors demo.

If you’re unfamiliar with time-of-flight sensors, they’re easy enough to understand. They measure distance by determining the time it takes photons to travel from one place to another. For example, by shooting out light from the sensor and measuring how long it takes to bounce back, the sensor can determine how far away an object is. Take an array of time-of-flight measurements, and you can get simple spatial data for further analysis.

The build uses an Arduino Uno R4 Minima, paired with a demo board for the VL53L5CX time-of-flight sensor. The software is developed using NanoEdge AI Studio. In a basic sense, the system uses a machine learning model to classify data captured by the time-of-flight sensor into gestures matching rock, paper, or scissors—or nothing, if no hand is present. If you don’t find [madmcu]’s tutorial enough, you can take a look at the original version from STMicroelectronics, too.

It takes some training, and it only works in the right lighting conditions, but this is a functional system that can determine real hand sign and play the game. We’ve seen similar techniques help more advanced robots cheat at this game before, too! What a time to be alive.

Rock, paper, scissors game that uses servos to choose one at random for the computer.

Forget ChatGPT And Play Rock-Paper-Scissors With Yourself Instead

This isn’t like the cool AI everyone’s getting caught up with these days, but we’re sure it will make a fun party gimmick nonetheless.

The premise of [CrazyScience]’s game is really simple, with three servos connected to labels that display rock, paper, and scissors, respectively. The game code is written to pick a label to display at random. Furthermore, an ultrasonic distance sensor detects when the player has moved their hand close to the game, indicating the player has chosen a hand and is challenging the game. The result of the game is decided by the player, so we imagine you could pretend you never lost and no one would know.

It would be cool to see the game support multiple players, keep score, or make sure you can never win. And you’ll probably want to add the randomSeed function in the code too. But that seems like a version two problem.

The only thing left to do is add some AI since that’s all we’re doing nowadays. But maybe you’re the type to enjoy the simple 8-bit pleasures instead. If you ask us though, we’d rather play with friends.

Continue reading “Forget ChatGPT And Play Rock-Paper-Scissors With Yourself Instead”

MIT Robots Fight With Lightsabers

Students of the MIT Robotics Lab decided to have some fun this holiday season with the big release of Star Wars. They built a lightsaber wielding delta-bot, and some very interesting hip-mounted lightsaber robot arms, akin to General Grievous.

First up in the video though is their Jedi Training robot, which is a variation of the delta-bot robot we’re all familiar with thanks to 3D printers. With a lightsaber mounted on top, it’s not too fast, but has a large range of motion to allow you to practice your lightsaber form. They call it the Triple Scissor Extender — and as you can imagine, it was built for something completely different. You can check out the designer’s personal blog here, though he doesn’t have any info on this particular project — yet.

Second is a robot they designed for a project called Supernumerary Robotic Limbs (SRL), which is literally designed to give you extra robotic arms — it was the next logical step to give them lightsabers…

Continue reading “MIT Robots Fight With Lightsabers”

Robot Cheats At Rock Paper Scissors

It is hard enough to beat computers at games like chess. Now robotics engineers at the Ishikawa Watanabe Laboratory in Japan have created a janken robot that wins every time (if you didn’t know, janken is the Japanese name for rock-paper-scissors). How can it win every time? Easy. It cheats.

The janken robot evolved through three different versions. In the first version, the robotic hand would note the human player’s hand with a high-speed camera and then move the hand to a winning counter play with about a 20 millisecond delay. In the second version, the delay was greatly reduced.

However, in the third version, the robot uses a scanning technique to capture an entire field of view and determines what play the human is making. Again, a winning counter play is instantly produced by the robotic hand.

Continue reading “Robot Cheats At Rock Paper Scissors”

Robotic Rock-paper-scissors Never Lets You Win

So robots kick our butts at tic-tac-toe, chess, Jeopardy, and now they’re the dominant species at rock-paper-scissors too. This robot arm will outmatch your at the game every single time. It’s not just fast enough to keep up, but it figures out what you’re planning to do and reacts according. All of this happens way to fast for you to catch it in the act.

Researchers at the University of Tokyo came up with the idea of combining high-speed vision with a high-speed hand. Apparently one millisecond is all it takes to analyze what move you’ve chosen. The time it takes for the hand to form the conquering position is only marginally longer than that. As you can see in the clip after the break, it already knows the protocol of 1-2-3 shoot and doesn’t need any operator intervention to start a new game, or repeatedly school you on trying to compete with a machine.

We’ve been beaten at the game by a machine before. This is just first time that the human player doesn’t need to wear special equipment and the machine has moved from a virtual hand to a physical one.

Continue reading “Robotic Rock-paper-scissors Never Lets You Win”