A question: if you’re controlling the classic video game Street Fighter with gestures, aren’t you just, you know, street fighting?

That’s a question [Charlie Gerard] is going to have to tackle should her AI gesture-recognition controller experiments take off. [Charlie] put together the game controller to learn more about the dark arts of machine learning in a fun and engaging way.

The controller consists of a battery-powered Arduino MKR1000 with WiFi and an MPU6050 accelerometer. Held in the hand, the controller streams accelerometer data to an external PC, capturing the characteristics of the motion. [Charlie] trained three different moves – a punch, an uppercut, and the dreaded Hadouken – and captured hundreds of examples of each. The raw data was massaged, converted to Tensors, and used to train a model for the three moves. Initial tests seem to work well. [Charlie] also made an online version that captures motion from your smartphone. The demo is explained in the video below; sadly, we couldn’t get more than three Hadoukens in before crashing it.

With most machine learning project seeming to concentrate on telling cats from dogs, this is a refreshing change. We’re seeing lots of offbeat machine learning projects these days, from cryptocurrency wallet attacks to a semi-creepy workout-monitoring gym camera.

We are excited to announce that UnlimitedHand is now an officially licensed Arduino AtHeart product. Created by Japanese startup H2L, the wearable controller straps around your forearm like an Ace bandage and allows you to actually touch and feel things within the gaming world.

UnlimitedHand consists of a 3D motion sensor, an array of muscle sensors, a multi-channel electronic muscle stimulator, and a vibration motor, which together, enable you to interact with objects and characters in VR. It does this by syncing the movement of a user’s hand and fingers with its virtual counterpart, and contracting the muscles on the wearer’s forearm to simulate haptic feedback.

With UnlimitedHand, not only will you be able to experience the ricochet of a gunshot or pet animals, but also hack various customized gestures thanks to its full compatibility with the Arduino IDE.

According to H2L:

Arduino, with their commitment to open-source, has reached out with their technology to muster a great force of Makers and inventors. This omni-present community has no doubt supported us in many ways during the development of UnlimitedHand. By joining the program, we can now present our results back to the community.

UnlimitedHand–which surpassed its Kickstarter goal in less than a day–is now available for purchase on Amazon and its website, as well as in retail stores throughout Japan.

Continue reading Cryoscope gadget simulates tomorrow's weather today (video)

Cryoscope gadget simulates tomorrow's weather today (video) originally appeared on Engadget on Mon, 06 Feb 2012 08:28:00 EST. Please see our terms for use of feeds.