Breathing Life into Feathers: Engineering a Hyper-Realistic Animatronic Raven
summary
Five servos drive coordinated head and body motion with per-servo speed, acceleration and safety bounds, driven from Python on a Raspberry Pi 5 and a Pololu Maestro controller. Audio clips are preprocessed once into RMS-based beak servo maps so prerecorded raven calls and mimicry match beak movement in real time. Face tracking uses HOG then a CNN to produce 128-dimension encodings compared against a database with 0.6 tolerance, timed tracking windows (23s active, 60s bored) and an MPR121 touch sensor for multi-channel contact.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 2:30Animatronic raven Samuel
- 4:40System architecture
- 7:34Natural movement design
- 10:27Face tracking mechanism
- 17:22Face detection code
- 21:48Reaction logic
- 26:47Future plans
- 31:42Lessons learned
- 34:02Q&A
related talks
19mBuild animatronics
28mChasing birds with code
40mFly like an Eagle
34mVoice-Controlled Lights on a Raspberry Pi
47mBuilding a Robot Arm with .NET 8, Raspberry Pi, Blazor and SignalR
33mLook mum, no hands!
49mBuilding a Raspberry Pi Robot Arm with .NET 6, Blazor and SignalR
46mControlling apps with your mind