Skip to the content
2 layers114 × 94 mmMega servos 1, the printed circuit board in 3D

Project VULCAN is an open humanoid robotics platform focused on expressive human-robot interaction through modular mechanical, electronic, and AI-driven subsystems.

Size
114 × 94 mm
Copper layers
2
Thickness
1.6 mm
Parts
46
Nets
86
Pads
202
Tracks, vias
249, 0
Routed
Yes
KiCad
KiCad 8.0 (file 20240108)
Created
28 May 2023
Updated
7 Sep 2026

Overview

Mega servos 1 is an open-source printed circuit board by ERC-BPGC, from the ERC-BPGC/project-vulcan repository on GitHub. It is a 2-layer board of 114 × 94 mm with 46 parts on 86 nets, routed with 249 tracks and 0 vias.

It belongs with the robots and motor control boards of this library.

README

README.md

Project VULCAN

Python ROS Status

vulcan

Project VULCAN is an open humanoid robotics platform focused on expressive human-robot interaction through modular mechanical, electronic, and AI-driven subsystems. It is a humanoid robot facial structure that can interact with humans — tracking faces, expressing emotions, hearing and speaking.

Current Status

Actively undergoing infrastructure modernization and subsystem stabilization before next-generation expansion.

Architecture Principles

  • Atomic modular subsystems.
  • Minimal cross-module interference.
  • Hardware/software separation.
  • Scalable pipelines for future contributors.
  • Experiment isolation via experiments/.

System Pipeline Overview

text
 Microphone Input
        ↓
 Speech-to-Text
        ↓
 Emotion + Context Fusion
        ↓
 LLM / RAG Pipeline
        ↓
 Response Generation
        ↓
 TTS + Mouth Movement + Facial Expressions

Features

  • Eyes — Independent 2-axis eyeball motion, eyelids, and gaze tracking via embedded cameras.
  • Mouth — Lip movement synced with speech and emotional expressions.
  • Eyebrows — Up/down motion to complement expressions.
  • Neck — 2-axis motion (horizontal 360° + vertical tilt).
  • Hearing & Speech — Microphone array for sound localisation, speech recognition, and TTS output.
  • Vision — Face detection, gaze estimation, emotion recognition (FER), hand-wave detection.
  • LLM Integration — RAG-augmented responses via GPT.

Demos

(GIF previews of eye tracking, blinking, mouth articulation, and emotion response coming soon!)

Hardware Stack

  • ESP32-CAM vision nodes.
  • Arduino Mega servo controller.
  • Custom servo PCB.
  • Embedded microphones.
  • Dual-camera eye subsystem.

Subsystems

Mechanical

  • Eye, eyelid & eyebrow subsystem — asymmetric eyeball motion with cameras, blinking, and brow movement.
  • Mouth subsystem — lip articulation for speech and emotion.
  • Neck subsystem — full pan and tilt.

Software

  • software/vision/ — face detection, gaze estimation (t_gaze.py), emotion recognition (m_model.py, m_expression.py), hand-wave detection.
  • software/speech/ — speech-to-text, TTS, voice selection.
  • software/llm/ — GPT interface and RAG pipeline for context-aware responses.
  • software/core/ — main driver (vulcan.py, vulcan2.py) coordinating all subsystems.

Electronics

  • Servo PCB (ESP32 & Mega variants) — custom KiCad boards in electronics/pcb/.
  • ESP32-CAM firmware — electronics/firmware/camera_esp/.
  • Arduino servo firmware — electronics/firmware/serial_arduino/.

Repository Structure

text
project-vulcan/
├── docs/                   # Install guides (CUDA, OpenCV, dlib), diagrams
├── software/
│   ├── core/               # Main entry points
│   ├── vision/             # CV modules
│   ├── speech/             # STT / TTS
│   ├── llm/                # GPT + RAG pipeline
│   │   └── rag/
│   ├── data/               # Knowledge base files for RAG
│   ├── utils/              # Shared helpers
│   ├── tools/              # Diagnostic scripts (check mic, list cameras)
│   ├── experiments/        # Prototypes and WIP scripts
│   ├── models/             # Model weights (gitignored — see models/README.md)
│   ├── archive/            # Deprecated code
│   └── requirements.txt
├── electronics/
│   ├── pcb/                # KiCad projects
│   ├── firmware/           # Arduino / ESP32 sketches
│   └── scripts/            # Python hardware-communication scripts
└── mechanical/             # CAD files (SolidWorks, Fusion, Blender, STL)
    ├── Eye_subsystem/
    ├── Mouth_Subsystem/
    ├── Head Structure/
    ├── Neck Base/
    └── base_holder/

Model weights are not tracked in git — see software/models/README.md for download links.
Install guides for CUDA, OpenCV, and dlib are in docs/

Getting Started

bash
# Install Python dependencies
pip install -r software/requirements.txt

# Download model weights (see software/models/README.md), then run
python software/core/vulcan2.py

Contributor Guidelines

  • New features should be isolated into modules.
  • Avoid editing archived or legacy systems.
  • Experimental work belongs in software/experiments/.
  • Shared utilities belong in software/utils/.
  • All hardware communication layers must remain abstracted.

Roadmap

  • ROS2 migration.
  • Improved facial animation pipeline.
  • Real-time multimodal emotion fusion.
  • Autonomous interaction routines.
  • Enhanced gaze tracking.
  • Full conversational memory system.

Built With

Downloading all the dependencies for running auto folder

  • Make sure cmake and cuda are already downloaded before doing this
  • Download the reurequirements.txt file
  • pip install -r requirements.txt

Limitations

  • The robot covers only the structure above the neck — no full-body mobility.

Core Contributors

Parts

46
QtyValueFootprintReferences
38Motor_ServoConnector_PinHeader_2.54mm:PinHeader_1x03_P2.54mm_VerticalM1, M2, M10, M11, M12, M13, M15, M16, M17, M18, M19, M20, M21, M22, M23, M24 +22
2AnalogConnector_PinSocket_2.54mm:PinSocket_1x08_P2.54mm_VerticalJ3, J5
1CommunicationConnector_PinSocket_2.54mm:PinSocket_1x08_P2.54mm_VerticalJ6
1Conn_01x02_SocketConnector_AMASS:AMASS_XT60-F_1x02_P7.20mm_VerticalJ8
1DigitalConnector_PinSocket_2.54mm:PinSocket_2x18_P2.54mm_VerticalJ7
1PWMConnector_PinSocket_2.54mm:PinSocket_1x08_P2.54mm_VerticalJ4
1PWMConnector_PinSocket_2.54mm:PinSocket_1x10_P2.54mm_VerticalJ2
1PowerConnector_PinSocket_2.54mm:PinSocket_1x08_P2.54mm_VerticalJ1

More from ERC-BPGC/project-vulcan

5
  • 2 layers29.4 × 37 mmServo pcb, the printed circuit board in 3D

    Servo pcb

    ERC-BPGC/project-vulcan

    Project VULCAN is an open humanoid robotics platform focused on expressive human-robot interaction through modular mechanical, electronic, and AI-driven subsystems.

    32 parts8
  • 2 layers49.5 × 70.5 mmServo pcb esp32, the printed circuit board in 3D

    Servo pcb esp32

    ERC-BPGC/project-vulcan

    Project VULCAN is an open humanoid robotics platform focused on expressive human-robot interaction through modular mechanical, electronic, and AI-driven subsystems.

    20 parts8
  • 2 layers23.6 × 17.6 mmMicrophone smd.step, the printed circuit board in 3D

    Microphone smd.step

    ERC-BPGC/project-vulcan

    Project VULCAN is an open humanoid robotics platform focused on expressive human-robot interaction through modular mechanical, electronic, and AI-driven subsystems.

    16 parts8
  • 2 layers56 × 34 mmMicrophone, the printed circuit board in 3D

    Microphone

    ERC-BPGC/project-vulcan

    Project VULCAN is an open humanoid robotics platform focused on expressive human-robot interaction through modular mechanical, electronic, and AI-driven subsystems.

    12 parts8
  • 2 layers19 × 19.5 mmESP CAM to ttl, the printed circuit board in 3D

    ESP CAM to ttl

    ERC-BPGC/project-vulcan

    Project VULCAN is an open humanoid robotics platform focused on expressive human-robot interaction through modular mechanical, electronic, and AI-driven subsystems.

    3 parts8

Similar boards

  • 2 layers83.3 × 65.3 mmSimonShield, the printed circuit board in 3D

    SimonShield

    github-linguist/linguist

    Language Savant. If your repository's language is being reported incorrectly, send us a pull request!

    46 parts14kMIT
  • 2 layers27.8 × 22.3 mmAudio, the printed circuit board in 3D

    Audio

    byrantech/laptop

    anyon_e, a highly integrated, high end, open source laptop. Attempt the impossible.

    46 parts4.3kMIT
  • 2 layers370 × 11 mmDaylight XXL, the printed circuit board in 3D

    Daylight XXL

    VoronDesign/Voron-Hardware

    Cool Hardware designed by the Voron Design group

    46 parts1.1kGPL-3.0
  • 2 layers87.5 × 50 mmMesabob, the printed circuit board in 3D

    Mesabob

    rene-dev/stmbl

    AC Servo Driver for STM32F4

    46 parts990GPL-3.0
  • 2 layers38.8 × 62.5 mmESPAudio, the printed circuit board in 3D

    ESPAudio

    hackclub/OnBoard

    💡 Join 1,000 teenagers and make your first PCB with a $100 grant!

    46 parts915
  • 2 layers53.2 × 24.8 mmPicoLink, the printed circuit board in 3D

    PicoLink

    ErichStyger/mcuoneclipse

    McuOnEclipse projects and examples

    46 parts765
  • 2 layers23 × 29 mmESP32-epaper adapter, the printed circuit board in 3D

    ESP32-epaper adapter

    pcbreflux/espressif

    all espressif stuff will committed here

    46 parts608GPL-3.0
  • 2 layers25.5 × 73.5 mmTERES PCB2-IO Rev.B, the printed circuit board in 3D

    TERES PCB2-IO Rev.B

    OLIMEX/DIY-LAPTOP

    Do It Yourself Open Source Hardware and Software Modular Hacker's Friendly Laptop

    46 parts578Apache-2.0

Questions

How big is the Mega servos 1 PCB?

It measures 114 × 94 mm and has 2 copper layers, 1.6 mm thick.

What parts does the Mega servos 1 use?

46 parts. The full list of its parts is on this page, with links to each part's symbol and footprint where PCBKit's library has them.

Where can I download the Mega servos 1 KiCad files?

From the ERC-BPGC/project-vulcan repository on GitHub, at the commit this page was made from: the board is Electronics/pcb/servopcb_mega/mega_servos_1.kicad_pcb and its schematic Electronics/pcb/ESP_CAM_to_ttl/ESP_CAM_to_ttl.kicad_sch. PCBKit opens the board in the browser, with nothing to install.

Can I use the Mega servos 1 design in my own project?

Its repository states no licence, so its author keeps all rights: ask ERC-BPGC before reusing the design.