Powered by TensorFlow: Creating a custom, machine learning-powered drumming arm
summary
A custom robotic drumming prosthetic reads muscle signals, trains a deep model on recorded EMG data, and runs inference on a small console so the arm predicts gestures and controls stick bounce in real time. The system uses EMG sensors for input, a TensorFlow model converted to TensorFlow Lite, and runs on a Raspberry Pi; latency is reported as essentially none, enabling near‑natural drumming and reliable, production‑like prototype performance.
AI-written summary · about
chapters (4)
related talks
41mCreating Intelligent Music Instruments with Machine Learning
24mCreating an AI Musician with JavaScript
34mThe hand prosthesis that learns from the user
55mBuilding with TensorFlow Lite for microcontrollers
28mMusic and AI in the Browser with TensorFlow js and Magenta js
26mBiosensor Machine Learning with Julia
23mMetaArms: Body Remapping Using Feet-Controlled Artificial Arms
28mStrike a Pose - Gesture recognition in JavaScript w/ ML & Arduino